{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/saga-a-fast-incremental-gradient-method-with","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","arxiv_id":"1407.0202","date":"2014-07-01","proceeding":"NeurIPS 2014 12","authors":["Aaron Defazio","Francis Bach","Simon Lacoste-Julien"],"abstract":"In this work we introduce a new optimisation method called SAGA in the spirit\nof SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient\nalgorithms with fast linear convergence rates. SAGA improves on the theory\nbehind SAG and SVRG, with better theoretical convergence rates, and has support\nfor composite objectives where a proximal operator is used on the regulariser.\nUnlike SDCA, SAGA supports non-strongly convex problems directly, and is\nadaptive to any inherent strong convexity of the problem. We give experimental\nresults showing the effectiveness of our method.","url_abs":"http://arxiv.org/abs/1407.0202v3","url_pdf":"http://arxiv.org/pdf/1407.0202v3.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":"saga-a-fast-incremental-gradient-method-with","repo_url":"https://github.com/PrzemyslawRys/Logistic-Regression-Lasso-Optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"saga-a-fast-incremental-gradient-method-with","repo_url":"https://github.com/kilianFatras/variance_reduced_neural_networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"saga-a-fast-incremental-gradient-method-with","repo_url":"https://github.com/adefazio/point-saga","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"saga-a-fast-incremental-gradient-method-with","repo_url":"https://github.com/scikit-learn-contrib/lightning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"saga-a-fast-incremental-gradient-method-with","repo_url":"https://github.com/scikit-learn/scikit-learn/blob/95119c13a/sklearn/linear_model/_logistic.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"saga","method_name":"SAGA"}],"datasets_introduced":[],"methods_introduced":[{"slug":"saga","name":"SAGA","full_name":"SAGA"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1407.0202","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}