{"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/an-inexact-variable-metric-proximal-point","title":"An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration","arxiv_id":"1610.00960","date":"2016-10-04","proceeding":null,"authors":["Hongzhou Lin","Julien Mairal","Zaid Harchaoui"],"abstract":"We propose an inexact variable-metric proximal point algorithm to accelerate\ngradient-based optimization algorithms. The proposed scheme, called QNing can\nbe notably applied to incremental first-order methods such as the stochastic\nvariance-reduced gradient descent algorithm (SVRG) and other randomized\nincremental optimization algorithms. QNing is also compatible with composite\nobjectives, meaning that it has the ability to provide exactly sparse solutions\nwhen the objective involves a sparsity-inducing regularization. When combined\nwith limited-memory BFGS rules, QNing is particularly effective to solve\nhigh-dimensional optimization problems, while enjoying a worst-case linear\nconvergence rate for strongly convex problems. We present experimental results\nwhere QNing gives significant improvements over competing methods for training\nmachine learning methods on large samples and in high dimensions.","url_abs":"http://arxiv.org/abs/1610.00960v4","url_pdf":"http://arxiv.org/pdf/1610.00960v4.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":"an-inexact-variable-metric-proximal-point","repo_url":"https://github.com/hongzhoulin89/Catalyst-QNing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}