{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/sgd/papers/ran/1","list_of":"/method/sgd","method":"SGD","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":192,"counts":{"archive_papers_tagged":2021,"with_a_code_link":591,"where_syntology_ran_a_sample":192,"not_listed_spam_title":0,"listed":2021,"listed_where_code_ran":192,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":161,"every_run_a_failure_of_syntologys_instrument":31,"listed_with_a_run_with_no_instrument_failure":161,"listed_every_run_a_failure_of_syntologys_instrument":31,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/sgd/papers/ran/1","prev":null,"next":"/method/sgd/papers/ran/2","papers":[{"paper":"/paper/sharpness-aware-machine-unlearning","slug":"sharpness-aware-machine-unlearning","title":"Sharpness-Aware Machine Unlearning","date":"2025-06-16","arxiv_id":"2506.13715","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/adams-momentum-itself-can-be-a-normalizer-for","slug":"adams-momentum-itself-can-be-a-normalizer-for","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","date":"2025-05-22","arxiv_id":"2505.16363","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pku-huzhang/AdamS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/sassha-sharpness-aware-adaptive-second-order","slug":"sassha-sharpness-aware-adaptive-second-order","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","date":"2025-02-25","arxiv_id":"2502.18153","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LOG-postech/Sassha"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-stronger-mixture-of-low-rank-experts-for","slug":"a-stronger-mixture-of-low-rank-experts-for","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","date":"2025-02-20","arxiv_id":"2502.15828","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thudm/moelora_riemannian"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/frugal-memory-efficient-optimization-by","slug":"frugal-memory-efficient-optimization-by","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","date":"2024-11-12","arxiv_id":"2411.07837","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fzmushko/frugal"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/active-dormant-attention-heads","slug":"active-dormant-attention-heads","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","date":"2024-10-17","arxiv_id":"2410.13835","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":6,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["guotianyu2000/active-dormant-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/sharpness-aware-minimization-efficiently","slug":"sharpness-aware-minimization-efficiently","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","date":"2024-10-14","arxiv_id":"2410.10373","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/sampa-sharpness-aware-minimization","slug":"sampa-sharpness-aware-minimization","title":"SAMPa: Sharpness-aware Minimization Parallelized","date":"2024-10-14","arxiv_id":"2410.10683","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lions-epfl/sampa"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/subzero-random-subspace-zeroth-order","slug":"subzero-random-subspace-zeroth-order","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","date":"2024-10-11","arxiv_id":"2410.08989","n_code_links":1,"syntology":{"ran":11,"of":15,"n_ran_checked":6,"n_instrument":5,"unverified":4,"pointer_only":15,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zimingyy/subzero"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/adam-exploits-ell-infty-geometry-of-loss","slug":"adam-exploits-ell-infty-geometry-of-loss","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","date":"2024-10-10","arxiv_id":"2410.08198","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mohamad-amin/adam-coordinate-adaptivity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pfdiff-training-free-acceleration-of","slug":"pfdiff-training-free-acceleration-of","title":"PFDiff: Training-free Acceleration of Diffusion Models through the Gradient Guidance of Past and Future","date":"2024-08-16","arxiv_id":"2408.08822","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":2,"n_instrument":6,"unverified":1,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","official":{"repos":["onefly123/PFDiff"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/2407-21633","slug":"2407-21633","title":"Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation","date":"2024-07-31","arxiv_id":"2407.21633","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["suntea233/duallora"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-gradient-descent-with-generalized","slug":"automatic-gradient-descent-with-generalized","title":"Gradient descent with generalized Newton's method","date":"2024-07-03","arxiv_id":"2407.02772","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shiyunxu/autogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-warmup-the-learning-rate-underlying","slug":"why-warmup-the-learning-rate-underlying","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","date":"2024-06-13","arxiv_id":"2406.09405","n_code_links":0,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/stochastic-polyak-step-sizes-and-momentum","slug":"stochastic-polyak-step-sizes-and-momentum","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","date":"2024-06-06","arxiv_id":"2406.04142","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["dimitris-oik/momsps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adafisher-adaptive-second-order-optimization","slug":"adafisher-adaptive-second-order-optimization","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","date":"2024-05-26","arxiv_id":"2405.16397","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":2,"n_instrument":5,"unverified":3,"pointer_only":10,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["AtlasAnalyticsLab/AdaFisher"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/does-sgd-really-happen-in-tiny-subspaces","slug":"does-sgd-really-happen-in-tiny-subspaces","title":"Does SGD really happen in tiny subspaces?","date":"2024-05-25","arxiv_id":"2405.16002","n_code_links":0,"syntology":{"ran":14,"of":15,"n_ran_checked":13,"n_instrument":1,"unverified":1,"pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/the-privacy-power-of-correlated-noise-in","slug":"the-privacy-power-of-correlated-noise-in","title":"The Privacy Power of Correlated Noise in Decentralized Learning","date":"2024-05-02","arxiv_id":"2405.01031","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["elfirdoussilab1/DECOR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/make-continual-learning-stronger-via-c-flat","slug":"make-continual-learning-stronger-via-c-flat","title":"Make Continual Learning Stronger via C-Flat","date":"2024-04-01","arxiv_id":"2404.00986","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":2,"n_instrument":6,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wannaa/c-flat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/differentially-private-next-token-prediction","slug":"differentially-private-next-token-prediction","title":"Differentially Private Next-Token Prediction of Large Language Models","date":"2024-03-22","arxiv_id":"2403.15638","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["james-flemings/pmixed"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-deep-neural-network-solutions-form-a-star","slug":"do-deep-neural-network-solutions-form-a-star","title":"Do Deep Neural Network Solutions Form a Star Domain?","date":"2024-03-12","arxiv_id":"2403.07968","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aktsonthalia/starlight"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-transformers-need-adam-a-hessian","slug":"why-transformers-need-adam-a-hessian","title":"Why Transformers Need Adam: A Hessian Perspective","date":"2024-02-26","arxiv_id":"2402.16788","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zyushun/hessian-spectrum"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/optex-expediting-first-order-optimization","slug":"optex-expediting-first-order-optimization","title":"OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations","date":"2024-02-18","arxiv_id":"2402.11427","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["youyve/OptEx"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-zeroth-order-optimization-for","slug":"revisiting-zeroth-order-optimization-for","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","date":"2024-02-18","arxiv_id":"2402.11592","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":3,"n_instrument":6,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zo-bench/zo-llm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-we-remove-the-square-root-in-adaptive","slug":"can-we-remove-the-square-root-in-adaptive","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","date":"2024-02-05","arxiv_id":"2402.03496","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["f-dangel/sirfshampoo","yorkerlin/remove-the-square-root"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethink-model-re-basin-and-the-linear-mode","slug":"rethink-model-re-basin-and-the-linear-mode","title":"Vanishing Feature: Diagnosing Model Merging and Beyond","date":"2024-02-05","arxiv_id":"2402.05966","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xingyuqu/rethink-re-basin","xingyuqu/vf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/riemannian-preconditioned-lora-for-fine","slug":"riemannian-preconditioned-lora-for-fine","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","date":"2024-02-04","arxiv_id":"2402.02347","n_code_links":1,"syntology":{"ran":15,"of":21,"n_ran_checked":11,"n_instrument":4,"unverified":6,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["pilancilab/Riemannian_Preconditioned_LoRA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/hift-a-hierarchical-full-parameter-fine","slug":"hift-a-hierarchical-full-parameter-fine","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","date":"2024-01-26","arxiv_id":"2401.15207","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["misonsky/HiFT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/momentum-sam-sharpness-aware-minimization","slug":"momentum-sam-sharpness-aware-minimization","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","date":"2024-01-22","arxiv_id":"2401.12033","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marlonbecker/msam"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/zo-adamu-optimizer-adapting-perturbation-by","slug":"zo-adamu-optimizer-adapting-perturbation-by","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","date":"2023-12-23","arxiv_id":"2312.15184","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mathisall/zo-adamu"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/tod-flow-modeling-the-structure-of-task","slug":"tod-flow-modeling-the-structure-of-task","title":"TOD-Flow: Modeling the Structure of Task-Oriented Dialogues","date":"2023-12-07","arxiv_id":"2312.04668","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["srsohn/tod-flow"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/agd-an-auto-switchable-optimizer-using-1","slug":"agd-an-auto-switchable-optimizer-using-1","title":"AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix","date":"2023-12-04","arxiv_id":"2312.01658","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["intelligent-machine-learning/atorch","intelligent-machine-learning/dlrover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/temperature-balancing-layer-wise-weight-1","slug":"temperature-balancing-layer-wise-weight-1","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","date":"2023-12-01","arxiv_id":"2312.00359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yefanzhou/tempbalance"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-effects-of-overparameterization-on","slug":"the-effects-of-overparameterization-on","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","date":"2023-11-29","arxiv_id":"2311.17539","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["log-postech/sam-overparam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mast-model-agnostic-sparsified-training","slug":"mast-model-agnostic-sparsified-training","title":"MAST: Model-Agnostic Sparsified Training","date":"2023-11-27","arxiv_id":"2311.16086","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["konstmish/opt_methods"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-from-free-text-human-feedback","slug":"learning-from-free-text-human-feedback","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","date":"2023-10-24","arxiv_id":"2310.15758","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ukplab/emnlp2023-learning-from-free-text-human-feedback"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/adam-through-a-second-order-lens","slug":"adam-through-a-second-order-lens","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","date":"2023-10-23","arxiv_id":"2310.14963","n_code_links":1,"syntology":{"ran":7,"of":16,"n_ran_checked":7,"n_instrument":0,"unverified":9,"pointer_only":16,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["rmclarke/adamthroughasecondorderlens"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-quadratic-synchronization-rule-for","slug":"a-quadratic-synchronization-rule-for","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","date":"2023-10-22","arxiv_id":"2310.14423","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hmgxr128/qsr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-predicting-and-better-resolving-1","slug":"understanding-predicting-and-better-resolving-1","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","date":"2023-10-06","arxiv_id":"2310.04411","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yueyang130/seem"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-do-we-need-weight-decay-in-modern-deep","slug":"why-do-we-need-weight-decay-in-modern-deep","title":"Why Do We Need Weight Decay in Modern Deep Learning?","date":"2023-10-06","arxiv_id":"2310.04415","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/why-weight-decay"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chunking-forgetting-matters-in-continual","slug":"chunking-forgetting-matters-in-continual","title":"Chunking: Continual Learning is not just about Distribution Shift","date":"2023-10-03","arxiv_id":"2310.02206","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tlee43/chunking-setting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-memorization-and-privacy-risks-of","slug":"on-memorization-and-privacy-risks-of","title":"On Memorization and Privacy Risks of Sharpness Aware Minimization","date":"2023-09-30","arxiv_id":"2310.00488","n_code_links":0,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/on-the-different-regimes-of-stochastic","slug":"on-the-different-regimes-of-stochastic","title":"On the different regimes of Stochastic Gradient Descent","date":"2023-09-19","arxiv_id":"2309.10688","n_code_links":1,"syntology":{"ran":9,"of":17,"n_ran_checked":9,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["pcsl-epfl/regimes_of_sgd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-the-robustness-difference","slug":"understanding-the-robustness-difference","title":"Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods","date":"2023-08-13","arxiv_id":"2308.06703","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["averyma/opt-robust"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bidirectional-looking-with-a-novel-double","slug":"bidirectional-looking-with-a-novel-double","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","date":"2023-07-02","arxiv_id":"2307.00631","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["chernyn/admeta-optimizer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/noise-stability-optimization-for-flat-minima","slug":"noise-stability-optimization-for-flat-minima","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","date":"2023-06-14","arxiv_id":"2306.08553","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["virtuosoresearch/noise-stability-optimization"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-diffusion-model","slug":"fast-diffusion-model","title":"Fast Diffusion Model","date":"2023-06-12","arxiv_id":"2306.06991","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":8,"n_instrument":6,"unverified":3,"pointer_only":9,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sail-sg/fdm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/stochastic-collapse-how-gradient-noise-1","slug":"stochastic-collapse-how-gradient-noise-1","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","date":"2023-06-07","arxiv_id":"2306.04251","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ccffccffcc/stochastic_collapse"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/decentralized-sgd-and-average-direction-sam","slug":"decentralized-sgd-and-average-direction-sam","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","date":"2023-06-05","arxiv_id":"2306.02913","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["raiden-zhu/icml-2023-dsgd-and-sam"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-sustainable-learning-coresets-for","slug":"towards-sustainable-learning-coresets-for","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","date":"2023-06-02","arxiv_id":"2306.01244","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bigml-cs-ucla/crest"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-impact-of-positional-encoding-on-length-1","slug":"the-impact-of-positional-encoding-on-length-1","title":"The Impact of Positional Encoding on Length Generalization in Transformers","date":"2023-05-31","arxiv_id":"2305.19466","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mcgill-nlp/length-generalization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-bayesian-approach-to-analysing-training-1","slug":"a-bayesian-approach-to-analysing-training-1","title":"A Bayesian Approach To Analysing Training Data Attribution In Deep Learning","date":"2023-05-31","arxiv_id":"2305.19765","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["elisanguyen/bayesian-tda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-rainbow-in-deep-network-black-boxes","slug":"a-rainbow-in-deep-network-black-boxes","title":"A Rainbow in Deep Network Black Boxes","date":"2023-05-29","arxiv_id":"2305.18512","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":11,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["florentinguth/rainbow"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/direction-oriented-multi-objective-learning","slug":"direction-oriented-multi-objective-learning","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","date":"2023-05-28","arxiv_id":"2305.18409","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-opt-lab/sdmgrad"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/rotational-optimizers-simple-robust-dnn","slug":"rotational-optimizers-simple-robust-dnn","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","date":"2023-05-26","arxiv_id":"2305.17212","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["epfml/req","epfml/rotational-optimizers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-characteristic-activation-value","slug":"neural-characteristic-activation-value","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","date":"2023-05-25","arxiv_id":"2305.15912","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Wenlin-Chen/geometric-parameterization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploiting-noise-as-a-resource-for","slug":"exploiting-noise-as-a-resource-for","title":"Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks","date":"2023-05-25","arxiv_id":"2305.16044","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["genema/Noisy-Spiking-Neuron-Nets"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/momo-momentum-models-for-adaptive-learning","slug":"momo-momentum-models-for-adaptive-learning","title":"MoMo: Momentum Models for Adaptive Learning Rates","date":"2023-05-12","arxiv_id":"2305.07583","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fabian-sp/MoMo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/tighter-lower-bounds-for-shuffling-sgd-random","slug":"tighter-lower-bounds-for-shuffling-sgd-random","title":"Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond","date":"2023-03-13","arxiv_id":"2303.07160","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/variance-reduced-clipping-for-non-convex","slug":"variance-reduced-clipping-for-non-convex","title":"Variance-reduced Clipping for Non-convex Optimization","date":"2023-03-02","arxiv_id":"2303.00883","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["haochuan-mit/varaince-reduced-clipping-for-non-convex-optimization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-and-when-does-local-sgd-generalize-better","slug":"why-and-when-does-local-sgd-generalize-better","title":"Why (and When) does Local SGD Generalize Better than SGD?","date":"2023-03-02","arxiv_id":"2303.01215","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hmgxr128/local-sgd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dropout-reduces-underfitting","slug":"dropout-reduces-underfitting","title":"Dropout Reduces Underfitting","date":"2023-03-02","arxiv_id":"2303.01500","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/dropout"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-unified-framework-for-soft-threshold","slug":"a-unified-framework-for-soft-threshold","title":"A Unified Framework for Soft Threshold Pruning","date":"2023-02-25","arxiv_id":"2302.13019","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yanqi-chen/lats"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dog-is-sgd-s-best-friend-a-parameter-free","slug":"dog-is-sgd-s-best-friend-a-parameter-free","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","date":"2023-02-08","arxiv_id":"2302.12022","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["formll/dog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/scale-up-with-order-finding-good-data","slug":"scale-up-with-order-finding-good-data","title":"Coordinating Distributed Example Orders for Provably Accelerated Training","date":"2023-02-02","arxiv_id":"2302.00845","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["garlguo/cd-grab"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-rate-free-learning-by-d-adaptation","slug":"learning-rate-free-learning-by-d-adaptation","title":"Learning-Rate-Free Learning by D-Adaptation","date":"2023-01-18","arxiv_id":"2301.07733","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/dadaptation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/modeldiff-a-framework-for-comparing-learning","slug":"modeldiff-a-framework-for-comparing-learning","title":"ModelDiff: A Framework for Comparing Learning Algorithms","date":"2022-11-22","arxiv_id":"2211.12491","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["madrylab/modeldiff"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/empirical-study-on-optimizer-selection-for","slug":"empirical-study-on-optimizer-selection-for","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","date":"2022-11-15","arxiv_id":"2211.08583","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":3,"n_instrument":4,"unverified":4,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["hiroki11x/optimizer_comparison_ood"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-kernel-based-view-of-language-model-fine","slug":"a-kernel-based-view-of-language-model-fine","title":"A Kernel-Based View of Language Model Fine-Tuning","date":"2022-10-11","arxiv_id":"2210.05643","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["princeton-nlp/lm-kernel-ft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/nag-gs-semi-implicit-accelerated-and-robust","slug":"nag-gs-semi-implicit-accelerated-and-robust","title":"NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer","date":"2022-09-29","arxiv_id":"2209.14937","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["skolai/nag-gs","naggsopt/naggs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimization-without-backpropagation","slug":"optimization-without-backpropagation","title":"Optimization without Backpropagation","date":"2022-09-13","arxiv_id":"2209.06302","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gbelouze/forward-gradient"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cram-a-compression-aware-minimizer","slug":"cram-a-compression-aware-minimizer","title":"CrAM: A Compression-Aware Minimizer","date":"2022-07-28","arxiv_id":"2207.14200","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["ist-daslab/cram"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tct-convexifying-federated-learning-using","slug":"tct-convexifying-federated-learning-using","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","date":"2022-07-13","arxiv_id":"2207.06343","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yaodongyu/tct"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-view-of-mini-batch-sgd-via-generating","slug":"a-view-of-mini-batch-sgd-via-generating","title":"A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta","date":"2022-06-22","arxiv_id":"2206.11124","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["godofnothing/powerlawoptimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/low-precision-stochastic-gradient-langevin-1","slug":"low-precision-stochastic-gradient-langevin-1","title":"Low-Precision Stochastic Gradient Langevin Dynamics","date":"2022-06-20","arxiv_id":"2206.09909","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ruqizhang/low-precision-sgld"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bayesian-estimation-of-differential-privacy","slug":"bayesian-estimation-of-differential-privacy","title":"Bayesian Estimation of Differential Privacy","date":"2022-06-10","arxiv_id":"2206.05199","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/responsible-ai-toolbox-privacy"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/integrating-random-effects-in-deep-neural","slug":"integrating-random-effects-in-deep-neural","title":"Integrating Random Effects in Deep Neural Networks","date":"2022-06-07","arxiv_id":"2206.03314","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gsimchoni/lmmnn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-theoretical-framework-for-inference","slug":"a-theoretical-framework-for-inference","title":"A Theoretical Framework for Inference Learning","date":"2022-06-01","arxiv_id":"2206.00164","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nalonso2/iltheory"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/re-parameterizing-your-optimizers-rather-than","slug":"re-parameterizing-your-optimizers-rather-than","title":"Re-parameterizing Your Optimizers rather than Architectures","date":"2022-05-30","arxiv_id":"2205.15242","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dingxiaoh/repoptimizers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/trainable-weight-averaging-for-fast","slug":"trainable-weight-averaging-for-fast","title":"Trainable Weight Averaging: A General Approach for Subspace Training","date":"2022-05-26","arxiv_id":"2205.13104","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["nblt/twa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/fedaug-reducing-the-local-learning-bias","slug":"fedaug-reducing-the-local-learning-bias","title":"FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction","date":"2022-05-26","arxiv_id":"2205.13462","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":6,"n_instrument":4,"unverified":5,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["lins-lab/fedbr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/grab-finding-provably-better-data","slug":"grab-finding-provably-better-data","title":"GraB: Finding Provably Better Data Permutations than Random Reshuffling","date":"2022-05-22","arxiv_id":"2205.10733","n_code_links":3,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["eugenelyc/grab"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/a-communication-efficient-distributed-3","slug":"a-communication-efficient-distributed-3","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","date":"2022-05-10","arxiv_id":"2205.05040","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mingruiliu-ml-lab/communication-efficient-local-gradient-clipping"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-you-see-is-what-you-get-distributional","slug":"what-you-see-is-what-you-get-distributional","title":"What You See is What You Get: Principled Deep Learning via Distributional Generalization","date":"2022-04-07","arxiv_id":"2204.03230","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yangarbiter/dp-dg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-efficient-and-scalable-sharpness","slug":"towards-efficient-and-scalable-sharpness","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","date":"2022-03-05","arxiv_id":"2203.02714","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/fast-convex-optimization-for-two-layer-relu","slug":"fast-convex-optimization-for-two-layer-relu","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","date":"2022-02-02","arxiv_id":"2202.01331","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["pilancilab/scnn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-structured-neural-networks-through-1","slug":"training-structured-neural-networks-through-1","title":"Training Structured Neural Networks Through Manifold Identification and Variance Reduction","date":"2021-12-05","arxiv_id":"2112.02612","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zihsyuan1214/rmda"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/simple-stochastic-and-online-gradient","slug":"simple-stochastic-and-online-gradient","title":"Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning","date":"2021-11-23","arxiv_id":"2111.12050","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhenhuan-yang/simple-pairwise"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/exponential-graph-is-provably-efficient-for","slug":"exponential-graph-is-provably-efficient-for","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","date":"2021-10-26","arxiv_id":"2110.13363","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Bluefog-Lib/bluefog","bluefog-lib/neurips2021-exponential-graph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-deep-neural-networks-with-adaptive","slug":"training-deep-neural-networks-with-adaptive","title":"Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization","date":"2021-10-18","arxiv_id":"2110.09057","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":7,"n_instrument":6,"unverified":4,"pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["kentaroy47/vision-transformers-cifar10"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/iglu-efficient-gcn-training-via-lazy-updates","slug":"iglu-efficient-gcn-training-via-lazy-updates","title":"IGLU: Efficient GCN Training via Lazy Updates","date":"2021-09-28","arxiv_id":"2109.13995","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sdeepaknarayanan/iglu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unrolling-sgd-understanding-factors","slug":"unrolling-sgd-understanding-factors","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","date":"2021-09-27","arxiv_id":"2109.13398","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cleverhans-lab/unrolling-sgd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/communication-efficient-federated-learning-8","slug":"communication-efficient-federated-learning-8","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","date":"2021-08-19","arxiv_id":"2108.08842","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["amitport/eden-distributed-mean-estimation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-matrix-free-approximations-of","slug":"efficient-matrix-free-approximations-of","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","date":"2021-07-07","arxiv_id":"2107.03356","n_code_links":2,"syntology":{"ran":7,"of":14,"n_ran_checked":4,"n_instrument":3,"unverified":7,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["IST-DASLab/M-FAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/open-set-label-noise-can-improve-robustness","slug":"open-set-label-noise-can-improve-robustness","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","date":"2021-06-21","arxiv_id":"2106.10891","n_code_links":4,"syntology":{"ran":17,"of":29,"n_ran_checked":10,"n_instrument":7,"unverified":12,"pointer_only":29,"phrase":"17 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified","official":{"repos":["hongxin001/ODNL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/multirate-training-of-neural-networks","slug":"multirate-training-of-neural-networks","title":"Multirate Training of Neural Networks","date":"2021-06-20","arxiv_id":"2106.10771","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tiffanyvlaar/multiratetrainingofnns"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-scale-private-learning-via-low-rank","slug":"large-scale-private-learning-via-low-rank","title":"Large Scale Private Learning via Low-rank Reparametrization","date":"2021-06-17","arxiv_id":"2106.09352","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["dayu11/Differentially-Private-Deep-Learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/locally-differentially-private-federated","slug":"locally-differentially-private-federated","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","date":"2021-06-17","arxiv_id":"2106.09779","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lowya/Locally-Differentially-Private-Federated-Learning","lowya/private-federated-learning-without-a-trusted-server"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-training-in-high-dimensions-via-block","slug":"robust-training-in-high-dimensions-via-block","title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","date":"2021-06-16","arxiv_id":"2106.08882","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["anishacharya/Optimization-Mavericks"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/debiasing-a-first-order-heuristic-for","slug":"debiasing-a-first-order-heuristic-for","title":"Debiasing a First-order Heuristic for Approximate Bi-level Optimization","date":"2021-06-04","arxiv_id":"2106.02487","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xingyousong/ufom"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"95f2717bc7eaf8cb00c901d8673df7b7d6350194a5820ff8cd411ffebffa1c35","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}