{"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/kalman-gradient-descent-adaptive-variance","title":"Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization","arxiv_id":"1810.12273","date":"2018-10-29","proceeding":null,"authors":["James Vuckovic"],"abstract":"We introduce Kalman Gradient Descent, a stochastic optimization algorithm\nthat uses Kalman filtering to adaptively reduce gradient variance in stochastic\ngradient descent by filtering the gradient estimates. We present both a\ntheoretical analysis of convergence in a non-convex setting and experimental\nresults which demonstrate improved performance on a variety of machine learning\nareas including neural networks and black box variational inference. We also\npresent a distributed version of our algorithm that enables large-dimensional\noptimization, and we extend our algorithm to SGD with momentum and RMSProp.","url_abs":"http://arxiv.org/abs/1810.12273v1","url_pdf":"http://arxiv.org/pdf/1810.12273v1.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":"kalman-gradient-descent-adaptive-variance","repo_url":"https://github.com/jamesvuc/KGD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.12273","atlas_url":"https://app.syntology.ai/?focus=1810.12273","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}