{"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/stochastic-optimization-with-variance","title":"Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure","arxiv_id":"1610.00970","date":"2016-10-04","proceeding":"NeurIPS 2017","authors":["Alberto Bietti","Julien Mairal"],"abstract":"Stochastic optimization algorithms with variance reduction have proven\nsuccessful for minimizing large finite sums of functions. Unfortunately, these\ntechniques are unable to deal with stochastic perturbations of input data,\ninduced for example by data augmentation. In such cases, the objective is no\nlonger a finite sum, and the main candidate for optimization is the stochastic\ngradient descent method (SGD). In this paper, we introduce a variance reduction\napproach for these settings when the objective is composite and strongly\nconvex. The convergence rate outperforms SGD with a typically much smaller\nconstant factor, which depends on the variance of gradient estimates only due\nto perturbations on a single example.","url_abs":"http://arxiv.org/abs/1610.00970v6","url_pdf":"http://arxiv.org/pdf/1610.00970v6.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":"stochastic-optimization-with-variance","repo_url":"https://github.com/albietz/stochs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.00970","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}