学术讲座

当前位置: 首页>> 科学研究>> 学术讲座>> 正文

光华讲坛—鲁棒与随机优化系列讲座(四):Learning-Based Robust Optimization: Procedures and Statistical Guarantees
发布时间: 2021-04-21

主题【鲁棒与随机优化系列讲座(四)】Learning-Based Robust Optimization: Procedures and Statistical

主讲人同济大学黄志源助理教授

主持人工商管理学院徐亮教授

时间2021年4月29日(星期四)14:00-15:00

直播平台及会议ID腾讯会议 会议ID:358 631 314

主办单位:工商管理学院科研处

主讲人简介:

黄志源博士现任同济大学经济与管理学院助理教授,他的主要研究领域为鲁棒优化、稀有事件仿真以及相关方法在人工智能系统与机器学习问题中的应用。研究成果发表于Management Science,IEEE Transactions on Intelligent Transportation Systems,以及Winter Simulation Conference (WSC),International Conference on Artificial Intelligence and Statistics (AISTATS)等国际学术刊物或学术会议。

内容提要:

Robust optimization (RO) is a common approach to tractably obtain safeguarding solutions for optimization problems with uncertain constraints. In this talk, we present a statistical framework to integrate data into RO based on learning a prediction set using (combinations of) geometric shapes that are compatible with established RO tools and on a simple data-splitting validation step that achieves finite-sample nonparametric statistical guarantees on feasibility. We demonstrate how our required sample size to achieve feasibility at a given confidence level is independent of the dimensions of both the decision space and the probability space governing the stochasticity, and we discuss some approaches to improve the objective performances while maintaining these dimension-free statistical feasibility guarantees.

鲁棒优化(RO)是求解不确定性约束优化问题的常用方法。本研究提出了一种统计学方法来学习并构建描述问题参数的不确定集合,并展示其良好的概率学性质,包括探讨问题参数落在不确定集中的概率保证等。