学术报告
当前位置: 首页 >> 学院新闻 >> 学术报告 >> 正文
Data-driven Piecewise Affine Decision Rule Methods for Stochastic Optimization with Covariate Information
发布日期:2023-10-11  来源:   查看次数:

报告时间:2023年10月13日(星期五)下午3:30-5:00

报告地点:第二学术报告厅

人:刘俊驿

工作单位:清华大学工业工程系

举办单位:合肥工业大学管理学院

报告简介:

In this talk, we focus on a class of stochastic optimization problems that minimize the conditionally expected cost given a new covariate feature. In real-world OR applications, without the prior knowledge of the conditional probability distribution, it is hard to obtain scenarios under the covariate feature of interest. To deal with this challenge, we propose a data-driven piecewise affine decision rule (PADR) method based on historical data pairs. We provide the first non-asymptotic consistency of the data-driven PADR-based method for a broad class of decision-making problems under a minimal Lipschitz continuity assumption of the optimal decision rule. To solve the PADR-based empirical risk minimization problem with a coupled nonconvex and nondifferentiable structure, we develop an enhanced stochastic majorization minimization algorithm and provide the first non-asymptotic convergence rate in terms of directional stationarity. Numerical results for both convex and nonconvex stochastic optimization problems with various nonlinear generating models indicates the superiority of the proposed data-driven method compared with the state-of-the-art data-driven methods.

报告人简介:

刘俊驿,清华大学工业工程系准聘副教授。2019年于美国南加州大学获得工业于系统工程博士学位,2015年于中国科学技术大学少年班学院获得统计专业学士学位。2019年9月至2021年3月在Prof. Jong-Shi Pang指导下从事博士后研究工作。目前研究方向为随机优化,侧重随机优化与统计、机器学习的交叉研究。以第一作者身份在Operations Research, Mathematics of Operations Research, SIAM Journal on Optimization等国际学术期刊上发表多篇文章。

上一条:Data-driven Convex Policy Optimization in an Assemble-to-order System
下一条:陈虎: 重塑全新的财务数字化体系

【关闭】