{"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/probabilistic-line-searches-for-stochastic","title":"Probabilistic Line Searches for Stochastic Optimization","arxiv_id":"1703.10034","date":"2017-03-29","proceeding":"NeurIPS 2015","authors":["Maren Mahsereci","Philipp Hennig"],"abstract":"In deterministic optimization, line searches are a standard tool ensuring\nstability and efficiency. Where only stochastic gradients are available, no\ndirect equivalent has so far been formulated, because uncertain gradients do\nnot allow for a strict sequence of decisions collapsing the search space. We\nconstruct a probabilistic line search by combining the structure of existing\ndeterministic methods with notions from Bayesian optimization. Our method\nretains a Gaussian process surrogate of the univariate optimization objective,\nand uses a probabilistic belief over the Wolfe conditions to monitor the\ndescent. The algorithm has very low computational cost, and no user-controlled\nparameters. Experiments show that it effectively removes the need to define a\nlearning rate for stochastic gradient descent.","url_abs":"http://arxiv.org/abs/1703.10034v2","url_pdf":"http://arxiv.org/pdf/1703.10034v2.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":"probabilistic-line-searches-for-stochastic","repo_url":"https://github.com/ProbabilisticNumerics/probabilistic_line_search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}