{"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":"/paper/compressing-gradient-optimizers-via-count","title":"Compressing Gradient Optimizers via Count-Sketches","arxiv_id":"1902.00179","date":"2019-02-01","proceeding":null,"authors":["Ryan Spring","Anastasios Kyrillidis","Vijai Mohan","Anshumali Shrivastava"],"abstract":"Many popular first-order optimization methods (e.g., Momentum, AdaGrad, Adam)\naccelerate the convergence rate of deep learning models. However, these\nalgorithms require auxiliary parameters, which cost additional memory\nproportional to the number of parameters in the model. The problem is becoming\nmore severe as deep learning models continue to grow larger in order to learn\nfrom complex, large-scale datasets. Our proposed solution is to maintain a\nlinear sketch to compress the auxiliary variables. We demonstrate that our\ntechnique has the same performance as the full-sized baseline, while using\nsignificantly less space for the auxiliary variables. Theoretically, we prove\nthat count-sketch optimization maintains the SGD convergence rate, while\ngracefully reducing memory usage for large-models. On the large-scale 1-Billion\nWord dataset, we save 25% of the memory used during training (8.6 GB instead of\n11.7 GB) by compressing the Adam optimizer in the Embedding and Softmax layers\nwith negligible accuracy and performance loss. For an Amazon extreme\nclassification task with over 49.5 million classes, we also reduce the training\ntime by 38%, by increasing the mini-batch size 3.5x using our count-sketch\noptimizer.","url_abs":"http://arxiv.org/abs/1902.00179v2","url_pdf":"http://arxiv.org/pdf/1902.00179v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"compressing-gradient-optimizers-via-count","repo_url":"https://github.com/rdspring1/Count-Sketch-Optimizers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"adagrad","method_name":"AdaGrad"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.00179","atlas_url":"https://app.syntology.ai/?focus=1902.00179","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1902.00179"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.00179\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.00179"},"call":"get_concepts_for_paper(arxiv_id=\"1902.00179\")"}],"by_repo":[{"repo":"rdspring1/Count-Sketch-Optimizers","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ead3343f6eda64e28ca9bab001bdd604947c0b6f3da8621bd5691d7bc56b5cef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}