{"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/21","list_of":"/method/sgd","method":"SGD","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":21,"pages_in_order":21,"rows_per_page":100,"rows":[2001,2021],"of":2021,"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","prev":"/method/sgd/papers/20","next":null,"papers":[{"paper":"/paper/on-the-computational-efficiency-of-training","slug":"on-the-computational-efficiency-of-training","title":"On the Computational Efficiency of Training Neural Networks","date":"2014-10-05","arxiv_id":"1410.1141","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"communication-efficient-distributed-dual","title":"Communication-Efficient Distributed Dual Coordinate Ascent","date":"2014-09-04","arxiv_id":"1409.1458","n_code_links":0,"syntology":null},{"paper":null,"slug":"randomized-block-coordinate-descent-for","title":"Randomized Block Coordinate Descent for Online and Stochastic Optimization","date":"2014-07-01","arxiv_id":"1407.0107","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-pyramid-pooling-in-deep-convolutional","slug":"spatial-pyramid-pooling-in-deep-convolutional","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","date":"2014-06-18","arxiv_id":"1406.4729","n_code_links":14,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"accelerating-minibatch-stochastic-gradient","title":"Accelerating Minibatch Stochastic Gradient Descent using Stratified Sampling","date":"2014-05-13","arxiv_id":"1405.3080","n_code_links":0,"syntology":null},{"paper":"/paper/some-improvements-on-deep-convolutional","slug":"some-improvements-on-deep-convolutional","title":"Some Improvements on Deep Convolutional Neural Network Based Image Classification","date":"2013-12-19","arxiv_id":"1312.5402","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-parallel-sgd-method-with-strong-convergence","title":"A Parallel SGD method with Strong Convergence","date":"2013-11-04","arxiv_id":"1311.0636","n_code_links":0,"syntology":null},{"paper":null,"slug":"stochastic-gradient-descent-weighted-sampling","title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","date":"2013-10-21","arxiv_id":"1310.5715","n_code_links":0,"syntology":null},{"paper":"/paper/online-tensor-methods-for-learning-latent","slug":"online-tensor-methods-for-learning-latent","title":"Online Tensor Methods for Learning Latent Variable Models","date":"2013-09-03","arxiv_id":"1309.0787","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-gradient-descent-for-drifting-least","title":"Fast gradient descent for drifting least squares regression, with application to bandits","date":"2013-07-11","arxiv_id":"1307.3176","n_code_links":0,"syntology":null},{"paper":null,"slug":"stochastic-approximation-for-speeding-up-lstd","title":"Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling","date":"2013-06-11","arxiv_id":"1306.2557","n_code_links":0,"syntology":null},{"paper":null,"slug":"stochastic-gradient-descent-algorithms-for","title":"Stochastic gradient descent algorithms for strongly convex functions at O(1/T) convergence rates","date":"2013-05-09","arxiv_id":"1305.2218","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-stochastic-strongly-convex","title":"Optimal Stochastic Strongly Convex Optimization with a Logarithmic Number of Projections","date":"2013-04-19","arxiv_id":"1304.5504","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-distance-metric-learning-by","title":"Efficient Distance Metric Learning by Adaptive Sampling and Mini-Batch Stochastic Gradient Descent (SGD)","date":"2013-04-03","arxiv_id":"1304.1192","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-neural-networks-with-stochastic","title":"Training Neural Networks with Stochastic Hessian-Free Optimization","date":"2013-01-16","arxiv_id":"1301.3641","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-distributed-deep-networks","title":"Large Scale Distributed Deep Networks","date":"2012-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"no-more-pesky-learning-rates","title":"No More Pesky Learning Rates","date":"2012-06-06","arxiv_id":"1206.1106","n_code_links":0,"syntology":null},{"paper":null,"slug":"beating-sgd-learning-svms-in-sublinear-time","title":"Beating SGD: Learning SVMs in Sublinear Time","date":"2011-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hogwild-a-lock-free-approach-to-parallelizing-1","title":"Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent","date":"2011-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hogwild-a-lock-free-approach-to-parallelizing","slug":"hogwild-a-lock-free-approach-to-parallelizing","title":"HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent","date":"2011-06-28","arxiv_id":"1106.5730","n_code_links":5,"syntology":{"ran":16,"of":24,"n_ran_checked":16,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":null,"slug":"provable-guarantees-on-learning-hierarchical","title":"Provable Guarantees on Learning Hierarchical Generative Models with Deep CNNs","date":null,"arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"8f62b7e9a74d1b5083c5cd8f9a1e06c18dc781fc1b83d8c2f9a491ec7dc73cf4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}