{"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/learning-structural-weight-uncertainty-for","title":"Learning Structural Weight Uncertainty for Sequential Decision-Making","arxiv_id":"1801.00085","date":"2017-12-30","proceeding":null,"authors":["Ruiyi Zhang","Chunyuan Li","Changyou Chen","Lawrence Carin"],"abstract":"Learning probability distributions on the weights of neural networks (NNs)\nhas recently proven beneficial in many applications. Bayesian methods, such as\nStein variational gradient descent (SVGD), offer an elegant framework to reason\nabout NN model uncertainty. However, by assuming independent Gaussian priors\nfor the individual NN weights (as often applied), SVGD does not impose prior\nknowledge that there is often structural information (dependence) among\nweights. We propose efficient posterior learning of structural weight\nuncertainty, within an SVGD framework, by employing matrix variate Gaussian\npriors on NN parameters. We further investigate the learned structural\nuncertainty in sequential decision-making problems, including contextual\nbandits and reinforcement learning. Experiments on several synthetic and real\ndatasets indicate the superiority of our model, compared with state-of-the-art\nmethods.","url_abs":"http://arxiv.org/abs/1801.00085v2","url_pdf":"http://arxiv.org/pdf/1801.00085v2.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":"learning-structural-weight-uncertainty-for","repo_url":"https://github.com/zhangry868/S2VGD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}