{"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/online-variance-reduction-with-mixtures","title":"Online Variance Reduction with Mixtures","arxiv_id":"1903.12416","date":"2019-03-29","proceeding":null,"authors":["Zalán Borsos","Sebastian Curi","Kfir. Y. Levy","Andreas Krause"],"abstract":"Adaptive importance sampling for stochastic optimization is a promising\napproach that offers improved convergence through variance reduction. In this\nwork, we propose a new framework for variance reduction that enables the use of\nmixtures over predefined sampling distributions, which can naturally encode\nprior knowledge about the data. While these sampling distributions are fixed,\nthe mixture weights are adapted during the optimization process. We propose\nVRM, a novel and efficient adaptive scheme that asymptotically recovers the\nbest mixture weights in hindsight and can also accommodate sampling\ndistributions over sets of points. We empirically demonstrate the versatility\nof VRM in a range of applications.","url_abs":"http://arxiv.org/abs/1903.12416v1","url_pdf":"http://arxiv.org/pdf/1903.12416v1.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":"online-variance-reduction-with-mixtures","repo_url":"https://github.com/zalanborsos/variance-reduction-mixtures","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.12416","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}