{"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/pruning/papers/26","list_of":"/method/pruning","method":"Pruning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":26,"pages_in_order":39,"rows_per_page":100,"rows":[2501,2600],"of":3874,"counts":{"archive_papers_tagged":3874,"with_a_code_link":1508,"where_syntology_ran_a_sample":478,"not_listed_spam_title":0,"listed":3874,"listed_where_code_ran":478,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":395,"every_run_a_failure_of_syntologys_instrument":83,"listed_with_a_run_with_no_instrument_failure":395,"listed_every_run_a_failure_of_syntologys_instrument":83,"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/pruning","prev":"/method/pruning/papers/25","next":"/method/pruning/papers/27","papers":[{"paper":null,"slug":"smof-squeezing-more-out-of-filters-yields","title":"SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning","date":"2021-10-21","arxiv_id":"2110.10842","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-strong-pruning-for-lottery-tickets","title":"Lottery Tickets with Nonzero Biases","date":"2021-10-21","arxiv_id":"2110.11150","n_code_links":0,"syntology":null},{"paper":"/paper/halp-hardware-aware-latency-pruning-1","slug":"halp-hardware-aware-latency-pruning-1","title":"HALP: Hardware-Aware Latency Pruning","date":"2021-10-20","arxiv_id":"2110.10811","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":null}},{"paper":null,"slug":"accelerating-framework-of-transformer-by","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","date":"2021-10-19","arxiv_id":"2110.10030","n_code_links":0,"syntology":null},{"paper":"/paper/improving-the-accuracy-memory-trade-off-of","slug":"improving-the-accuracy-memory-trade-off-of","title":"Improving the Accuracy-Memory Trade-Off of Random Forests Via Leaf-Refinement","date":"2021-10-19","arxiv_id":"2110.10075","n_code_links":1,"syntology":null},{"paper":"/paper/sosp-efficiently-capturing-global-1","slug":"sosp-efficiently-capturing-global-1","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","date":"2021-10-19","arxiv_id":"2110.11395","n_code_links":1,"syntology":null},{"paper":null,"slug":"bermo-what-can-bert-learn-from-elmo-1","title":"BERMo: What can BERT learn from ELMo?","date":"2021-10-18","arxiv_id":"2110.15802","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-everything-within-random-binary","title":"Finding Everything within Random Binary Networks","date":"2021-10-18","arxiv_id":"2110.08996","n_code_links":0,"syntology":null},{"paper":"/paper/graph-less-neural-networks-teaching-old-mlps-1","slug":"graph-less-neural-networks-teaching-old-mlps-1","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","date":"2021-10-17","arxiv_id":"2110.08727","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"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) · 1 unverified","official":{"repos":["snap-research/graphless-neural-networks"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"s-cyc-a-learning-rate-schedule-for-iterative","title":"S-Cyc: A Learning Rate Schedule for Iterative Pruning of ReLU-based Networks","date":"2021-10-17","arxiv_id":"2110.08764","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-metric-for-evaluating-semantics-1","slug":"a-novel-metric-for-evaluating-semantics-1","title":"A Novel Metric for Evaluating Semantics Preservation","date":"2021-10-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-unified-speaker-adaptation-approach-for-asr","slug":"a-unified-speaker-adaptation-approach-for-asr","title":"A Unified Speaker Adaptation Approach for ASR","date":"2021-10-16","arxiv_id":"2110.08545","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-cooperation-and-online-planning","title":"Learning Cooperation and Online Planning Through Simulation and Graph Convolutional Network","date":"2021-10-16","arxiv_id":"2110.08480","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-network-pruning-through-constrained","title":"Neural Network Pruning Through Constrained Reinforcement Learning","date":"2021-10-16","arxiv_id":"2110.08558","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-do-compressed-large-language-models","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","date":"2021-10-16","arxiv_id":"2110.08419","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentiable-network-pruning-for","title":"Differentiable Network Pruning for Microcontrollers","date":"2021-10-15","arxiv_id":"2110.08350","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-representations-for-privacy-1","title":"Efficient privacy-preserving inference for convolutional neural networks","date":"2021-10-15","arxiv_id":"2110.08321","n_code_links":0,"syntology":null},{"paper":"/paper/fire-together-wire-together-a-dynamic-pruning","slug":"fire-together-wire-together-a-dynamic-pruning","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","date":"2021-10-15","arxiv_id":"2110.08232","n_code_links":1,"syntology":null},{"paper":"/paper/joint-channel-and-weight-pruning-for-model","slug":"joint-channel-and-weight-pruning-for-model","title":"Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices","date":"2021-10-15","arxiv_id":"2110.08013","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparse-progressive-distillation-resolving","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","date":"2021-10-15","arxiv_id":"2110.08190","n_code_links":0,"syntology":null},{"paper":"/paper/training-deep-neural-networks-with-joint","slug":"training-deep-neural-networks-with-joint","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","date":"2021-10-15","arxiv_id":"2110.08271","n_code_links":2,"syntology":null},{"paper":null,"slug":"fedspeech-federated-text-to-speech-with","title":"FedSpeech: Federated Text-to-Speech with Continual Learning","date":"2021-10-14","arxiv_id":"2110.07216","n_code_links":0,"syntology":null},{"paper":null,"slug":"traceback-of-data-poisoning-attacks-in-neural","title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks","date":"2021-10-13","arxiv_id":"2110.06904","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-bayesian-network-structure-learning","slug":"efficient-bayesian-network-structure-learning","title":"Efficient Bayesian network structure learning via local Markov boundary search","date":"2021-10-12","arxiv_id":"2110.06082","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"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) · 2 unverified","official":{"repos":["minggao97/tam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-forward-indexes-for-efficient-document","slug":"fast-forward-indexes-for-efficient-document","title":"Efficient Neural Ranking using Forward Indexes","date":"2021-10-12","arxiv_id":"2110.06051","n_code_links":1,"syntology":null},{"paper":"/paper/program-transfer-and-ontology-awareness-for","slug":"program-transfer-and-ontology-awareness-for","title":"Program Transfer for Answering Complex Questions over Knowledge Bases","date":"2021-10-12","arxiv_id":"2110.05743","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-lottery-ticket-wins-a-theoretical-1","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","date":"2021-10-12","arxiv_id":"2110.05667","n_code_links":0,"syntology":null},{"paper":null,"slug":"compact-cnn-models-for-on-device-ocular-based","title":"Compact CNN Models for On-device Ocular-based User Recognition in Mobile Devices","date":"2021-10-11","arxiv_id":"2110.04953","n_code_links":0,"syntology":null},{"paper":null,"slug":"perturbation-theory-aided-learned-digital","title":"Perturbation Theory-Aided Learned Digital Back-Propagation Scheme for Optical Fiber Nonlinearity Compensation","date":"2021-10-11","arxiv_id":"2110.05563","n_code_links":0,"syntology":null},{"paper":"/paper/nvit-vision-transformer-compression-and-1","slug":"nvit-vision-transformer-compression-and-1","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","date":"2021-10-10","arxiv_id":"2110.04869","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":null}},{"paper":"/paper/vectorization-of-raster-manga-by-deep","slug":"vectorization-of-raster-manga-by-deep","title":"MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning","date":"2021-10-10","arxiv_id":"2110.04830","n_code_links":1,"syntology":null},{"paper":"/paper/weight-evolution-improving-deep-neural","slug":"weight-evolution-improving-deep-neural","title":"Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values","date":"2021-10-09","arxiv_id":"2110.04492","n_code_links":1,"syntology":null},{"paper":"/paper/abcp-automatic-block-wise-and-channel-wise","slug":"abcp-automatic-block-wise-and-channel-wise","title":"ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search","date":"2021-10-08","arxiv_id":"2110.03858","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-optimizations-on-deep-noise","title":"Performance optimizations on deep noise suppression models","date":"2021-10-08","arxiv_id":"2110.04378","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesizing-video-trajectory-queries","title":"Synthesizing Video Trajectory Queries","date":"2021-10-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-supermask-pruning-learning-to","slug":"end-to-end-supermask-pruning-learning-to","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","date":"2021-10-07","arxiv_id":"2110.03298","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jiahuei/sparse-image-captioning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/layer-wise-pruning-of-transformer-attention","slug":"layer-wise-pruning-of-transformer-attention","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","date":"2021-10-07","arxiv_id":"2110.03252","n_code_links":1,"syntology":null},{"paper":"/paper/the-low-resource-double-bind-an-empirical","slug":"the-low-resource-double-bind-an-empirical","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","date":"2021-10-06","arxiv_id":"2110.03036","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-interplay-between-sparsity-naturalness","title":"On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis","date":"2021-10-04","arxiv_id":"2110.01147","n_code_links":0,"syntology":null},{"paper":"/paper/learning-compact-representations-of-neural","slug":"learning-compact-representations-of-neural","title":"Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)","date":"2021-10-01","arxiv_id":"2110.00684","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["jayroxis/dam-pytorch"],"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","unlocated"]}}},{"paper":"/paper/powerpropagation-a-sparsity-inducing-weight","slug":"powerpropagation-a-sparsity-inducing-weight","title":"Powerpropagation: A sparsity inducing weight reparameterisation","date":"2021-10-01","arxiv_id":"2110.00296","n_code_links":2,"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":{"repos":["deepmind/deepmind-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"deep-neural-compression-via-concurrent","title":"Deep Neural Compression Via Concurrent Pruning and Self-Distillation","date":"2021-09-30","arxiv_id":"2109.15014","n_code_links":0,"syntology":null},{"paper":null,"slug":"red-data-free-pruning-of-deep-neural-networks","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","date":"2021-09-30","arxiv_id":"2110.01397","n_code_links":0,"syntology":null},{"paper":null,"slug":"ambiguity-adaptive-inference-and-single-shot","title":"Ambiguity Adaptive Inference and Single-shot based Channel Pruning for Satellite Processing Environments","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-channel-pruning-with-learned","title":"Automated Channel Pruning with Learned Importance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"can-network-pruning-benefit-deep-learning","title":"Can network pruning benefit deep learning under label noise?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-compression","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","date":"2021-09-29","arxiv_id":"2109.14710","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-distillation-using","title":"Cross-Architecture Distillation Using Bidirectional CMOW Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dice-a-simple-sparsification-method-for-out","title":"DICE: A Simple Sparsification Method for Out-of-distribution Detection","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-ensembles-of-graph-neural-networks","title":"Efficient Ensembles of Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-winning-tickets-drawing-over-fine","title":"Efficient Winning Tickets Drawing over Fine-Grained Structured Sparsity","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-ai-based-dynamic-filter-pruning","title":"EXPLAINABLE AI-BASED DYNAMIC FILTER PRUNING OF CONVOLUTIONAL NEURAL NETWORKS","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/global-magnitude-pruning-with-minimum","slug":"global-magnitude-pruning-with-minimum","title":"Global Magnitude Pruning With Minimum Threshold Is All We Need","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hfsp-a-hardware-friendly-soft-pruning","title":"HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-interactions-among-categorical","title":"Identifying Interactions among Categorical Predictors with Monte-Carlo Tree Search","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"inductive-lottery-ticket-learning-for-graph","title":"Inductive Lottery Ticket Learning for Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"iprune-a-magnitude-based-unstructured-pruning","title":"iPrune: A Magnitude Based Unstructured Pruning Method for Efficient Binary Networks in Hardware","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lean-graph-based-pruning-for-convolutional-1","title":"LEAN: graph-based pruning for convolutional neural networks by extracting longest chains","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-efficient-image-super-resolution","title":"Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-pruning-friendly-networks-via-frank","slug":"learning-pruning-friendly-networks-via-frank","title":"Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-sparse-dnns-with-soft-thresholding","title":"Learning sparse DNNs with soft thresholding of weights during training","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lottery-image-prior","title":"Lottery Image Prior","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lottery-ticket-structured-node-pruning-for","title":"Lottery Ticket Structured Node Pruning for Tabular Datasets","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lottery-tickets-can-have-structural-sparsity","title":"Lottery Tickets can have Structural Sparsity","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"network-pruning-optimization-by-simulated","title":"Network Pruning Optimization by Simulated Annealing Algorithm","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-efficiency-of-deep-neural-networks","title":"On the Efficiency of Deep Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ossum-a-gradient-free-approach-for-pruning","title":"OSSuM: A Gradient-Free Approach For Pruning Neural Networks At Initialization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"proving-the-lottery-ticket-hypothesis-for","title":"Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-again-the-value-of-network-pruning","title":"Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/revisit-kernel-pruning-with-lottery-regulated","slug":"revisit-kernel-pruning-with-lottery-regulated","title":"Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-the-lottery-ticket-hypothesis-a","title":"Revisiting the Lottery Ticket Hypothesis: A Ramanujan Graph Perspective","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"self-distilled-pruning-of-neural-networks","title":"Self-Distilled Pruning Of Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"self-slimming-vision-transformer","title":"Self-Slimming Vision Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spark-co-exploring-model-sparsity-and-low","title":"SPARK: co-exploring model SPArsity and low-RanKness for compact neural networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-unbalanced-gan-training-with-in-time","title":"Sparse Unbalanced GAN Training with In-Time Over-Parameterization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-pruning-meets-orthogonality","title":"Structured Pruning Meets Orthogonality","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"succinct-compression-near-optimal-and","title":"Succinct Compression: Near-Optimal and Lossless Compression of Deep Neural Networks during Inference Runtime","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"takeuchi-s-information-criteria-as","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-on-chip-training-of-quantum","title":"Towards Efficient On-Chip Training of Quantum Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tropical-geometrical-zonotope-reduction-as","title":"Tropical Geometrical Zonotope Reduction as Applied to Neural Network Compression.","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"universality-of-deep-neural-network-lottery-1","title":"Universality of Deep Neural Network Lottery Tickets: A Renormalization Group Perspective","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"variance-pruning-pruning-language-models-via","title":"Variance Pruning: Pruning Language Models via Temporal Neuron Variance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vote-for-nearest-neighbors-meta-pruning-of","title":"Vote for Nearest Neighbors Meta-Pruning of Self-Supervised Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-prunability-of-attention-heads-in","title":"On the Prunability of Attention Heads in Multilingual BERT","date":"2021-09-26","arxiv_id":"2109.12683","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-density-estimation-for-density-based","title":"Fast Density Estimation for Density-based Clustering Methods","date":"2021-09-23","arxiv_id":"2109.11383","n_code_links":0,"syntology":null},{"paper":"/paper/high-dimensional-bayesian-optimization-for","slug":"high-dimensional-bayesian-optimization-for","title":"Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning","date":"2021-09-22","arxiv_id":"2109.10591","n_code_links":1,"syntology":null},{"paper":"/paper/neural-network-relief-a-pruning-algorithm","slug":"neural-network-relief-a-pruning-algorithm","title":"Neural network relief: a pruning algorithm based on neural activity","date":"2021-09-22","arxiv_id":"2109.10795","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-and-efficient-moe-training-for","slug":"scalable-and-efficient-moe-training-for","title":"Scalable and Efficient MoE Training for Multitask Multilingual Models","date":"2021-09-22","arxiv_id":"2109.10465","n_code_links":1,"syntology":null},{"paper":"/paper/comparing-rewinding-and-fine-tuning-in-neural-1","slug":"comparing-rewinding-and-fine-tuning-in-neural-1","title":"Reproducibility Study: Comparing Rewinding and Fine-tuning in Neural Network Pruning","date":"2021-09-20","arxiv_id":"2109.09670","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-pattern-pruning-using","title":"Structured Pattern Pruning Using Regularization","date":"2021-09-18","arxiv_id":"2109.08814","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-linguistic-context-for-language","slug":"distilling-linguistic-context-for-language","title":"Distilling Linguistic Context for Language Model Compression","date":"2021-09-17","arxiv_id":"2109.08359","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["geondopark/ckd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/new-students-on-sesame-street-what-order","slug":"new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","n_code_links":1,"syntology":null},{"paper":null,"slug":"dense-pruning-of-pointwise-convolutions-in","title":"Dense Pruning of Pointwise Convolutions in the Frequency Domain","date":"2021-09-16","arxiv_id":"2109.07707","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-fly-ensemble-pruning-in-evolving-data","title":"On-the-Fly Ensemble Pruning in Evolving Data Streams","date":"2021-09-15","arxiv_id":"2109.07611","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimising-rolling-stock-planning-including","title":"Optimising Rolling Stock Planning including Maintenance with Constraint Programming and Quantum Annealing","date":"2021-09-15","arxiv_id":"2109.07212","n_code_links":0,"syntology":null},{"paper":null,"slug":"realization-of-neural-network-based-optical","title":"Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization","date":"2021-09-15","arxiv_id":"2109.07204","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapruner-adaptive-channel-pruning-and","title":"AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance","date":"2021-09-14","arxiv_id":"2109.06397","n_code_links":0,"syntology":null},{"paper":"/paper/the-stem-cell-hypothesis-dilemma-behind-multi","slug":"the-stem-cell-hypothesis-dilemma-behind-multi","title":"The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders","date":"2021-09-14","arxiv_id":"2109.06939","n_code_links":1,"syntology":null},{"paper":"/paper/causal-explanation-of-convolutional-neural","slug":"causal-explanation-of-convolutional-neural","title":"Causal Explanation of Convolutional Neural Networks","date":"2021-09-13","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"8f75472a67763098de2d26fcae59612e64f639be9d37f80a84471167fbb876c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}