{"id":23360,"date":"2024-11-28T21:19:05","date_gmt":"2024-11-28T18:19:05","guid":{"rendered":"https:\/\/w3.bilkent.edu.tr\/en\/?p=23360"},"modified":"2024-12-01T22:24:28","modified_gmt":"2024-12-01T19:24:28","slug":"ee-seminar-structured-decision-making-under-uncertainty-optimization-and-generalization-under-constraints-jiawei-zhang-400pm-november-29-2024-en","status":"publish","type":"post","link":"https:\/\/w3.bilkent.edu.tr\/en\/ee-seminar-structured-decision-making-under-uncertainty-optimization-and-generalization-under-constraints-jiawei-zhang-400pm-november-29-2024-en\/","title":{"rendered":"EE Seminar: \u201cStructured Decision-Making under Uncertainty: Optimization and Generalization under Constraints\u201d, Jiawei Zhang, 4:00PM November 29 2024 (EN)"},"content":{"rendered":"<p>EEE 591\/592 Seminar:<\/p>\n<p>Structured Decision-Making under Uncertainty: Optimization and Generalization under Constraints<\/p>\n<p>Dr. Jiawei Zhang<br \/>\nMassachusetts Institute of Technology<\/p>\n<p>Date\/Time: Friday, November 29, 2024 at 16:00-17:00 TSI<br \/>\nPlace: Zoom<\/p>\n<p>This is an online seminar. To request event details please send a message to department.<\/p>\n<p>Abstract: Problems in decision-making under uncertainty often need to be tackled under limitations such as lack of high quality data with good coverage, random and adversarial perturbations, incomplete knowledge of the underlying model, and limited resources. This talk will outline a framework to address these challenges based on advances in optimization theory and statistical learning. Drawing from examples in machine learning, cyber-physical systems, and operations research, we discuss two key innovations:<\/p>\n<ol>\n<li>Efficient algorithms for constrained optimization problems:<br \/>\nThese arise in optimal resource allocation and decision-making under a dynamic environment or worst-case perturbations. By utilizing structural properties, specifically error bounds\/perturbation bounds, we develop simple algorithms to achieve optimal iteration complexity.<\/li>\n<li>Generalizable algorithms:<br \/>\nThese guarantee that decision policies learned from imperfect historical data can generalize to unseen data. By deriving and leveraging the structure of error bounds, we develop a constrained optimization approach to help us find a nearly optimal policy from imperfect data with nearly optimal sample complexity.<\/li>\n<\/ol>\n<p>In addition, we briefly discuss progress in contextual optimization, where we leverage constrained optimization techniques and structural properties to learn good policies using contextual data, even under model misspecification. These developments set the stage for decision-making, generation, and prediction in uncertain, dynamic environments to satisfy users\u2019 requirements and preferences under resource limits.<\/p>\n<p>Biography: Jiawei Zhang is an incoming assistant professor in the Department of Computer Sciences at the University of Wisconsin-Madison. Currently, he is a postdoctoral fellow supported by The MIT Postdoctoral Fellowship for Engineering Excellence in the Laboratory for Information &amp; Decision Systems (LIDS) at MIT, working with Prof. Asuman Ozdaglar and Prof. Saurabh Amin. He obtained his PhD in Computer and Information Engineering from the Chinese University of Hong Kong, Shenzhen, under the supervision of Prof. Zhi-Quan (Tom) Luo, and was awarded the Presidential Award for Outstanding Doctoral Students. Previously, he earned his BSc in Mathematics (Hua Loo-Keng Talent Program) from the University of Science and Technology of China.<\/p>\n<p>His research interests include:<br \/>\n\u2022 Optimization theory and algorithms with applications in machine learning, energy, and signal processing \u2022 Optimization, generalization, and robustness of machine learning, reinforcement learning, generative models (including diffusion models, large models, foundation models).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>EEE 591\/592 Seminar: Structured Decision-Making under Uncertainty: Optimization and Generalization under Constraints Dr. Jiawei Zhang Massachusetts Institute of Technology Date\/Time: Friday, November 29, 2024 at 16:00-17:00 TSI Place: Zoom This is an online seminar. To request event details please send a message to department. Abstract: Problems in decision-making under uncertainty [\u2026] <\/p>\n<div class=\"clear\"><\/div>\n<p><a class=\"more_link clearfix\" href=\"https:\/\/w3.bilkent.edu.tr\/en\/ee-seminar-structured-decision-making-under-uncertainty-optimization-and-generalization-under-constraints-jiawei-zhang-400pm-november-29-2024-en\/\" rel=\"nofollow\">Read More<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12],"tags":[],"class_list":["post-23360","post","type-post","status-publish","format-standard","hentry","category-oldposts"],"_links":{"self":[{"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/posts\/23360","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/comments?post=23360"}],"version-history":[{"count":1,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/posts\/23360\/revisions"}],"predecessor-version":[{"id":23361,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/posts\/23360\/revisions\/23361"}],"wp:attachment":[{"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/media?parent=23360"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/categories?post=23360"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/en\/wp-json\/wp\/v2\/tags?post=23360"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}