{"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/gradient-descent-revisited-via-an-adaptive","title":"Gradient descent revisited via an adaptive online learning rate","arxiv_id":"1801.09136","date":"2018-01-27","proceeding":null,"authors":["Mathieu Ravaut","Satya Gorti"],"abstract":"Any gradient descent optimization requires to choose a learning rate. With\ndeeper and deeper models, tuning that learning rate can easily become tedious\nand does not necessarily lead to an ideal convergence. We propose a variation\nof the gradient descent algorithm in the which the learning rate is not fixed.\nInstead, we learn the learning rate itself, either by another gradient descent\n(first-order method), or by Newton's method (second-order). This way, gradient\ndescent for any machine learning algorithm can be optimized.","url_abs":"http://arxiv.org/abs/1801.09136v2","url_pdf":"http://arxiv.org/pdf/1801.09136v2.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":"gradient-descent-revisited-via-an-adaptive","repo_url":"https://github.com/UrosOgrizovic/SimpleGoogleQuickdraw","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"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}