Mathematical Optimization in Machine Learning/Decision Making

Abstract

The speaker will present a few recent mathematical optimization real world case studies in Data Science and Machine-Learning. He will show how newly developed optimization models and numerical algorithms/solvers can be effectively used to achieve learning and decision-making efficiency and optimality in many fields, including Policy Training in Reinforcement Learning, Wireless Ad-Hoc Sensor Network Localization/Tracking, Service Covering and Partitioning, Energy Management and Optimal PEV Charging/Discharging, Dynamic Unit-Commitment (to balance demand and supply) for Power-Grid, and High-Speed Railway Scheduling.

About the Speaker

Prof. YE Yinyu is currently the K.T. Li Chair Professor of Engineering at Department of Management Science and Engineering and Institute of Computational and Mathematical Engineering, Stanford University. He received the BS degree in System Engineering from the Huazhong University of Science and Technology, China, and the MS and PhD degrees in Engineering-Economic Systems and Operations Research from Stanford University.

Prof. Ye’s current research interests include Continuous and Discrete Optimization, Data Science and Applications, Computational Algorithm Design and Analyses, Algorithmic Game/Market Equilibrium; and he was one of the pioneers of Interior-Point Methods, Conic Linear Programming, Distributionally Robust Optimization, Online Linear Programming, Algorithm Analyses for Reinforcement Learning and Markov Decision Process, and etc.

Prof. Ye has received several academic awards including: the inaugural 2006 Farkas Prize on Optimization, the 2009 IBM Faculty Award, the 2009 John van Neumann Theory Prize for fundamental sustained contributions to theory in Operations Research and the Management Sciences, the inaugural 2012 ISMP Tseng Lectureship Prize for outstanding contribution to continuous optimization (every three years), the winner of the 2014 SIAM Optimization Prize awarded (every three years), the 2015 SPS Signal Processing Magazine Best Paper Award, etc.. He has supervised numerous doctoral students at Stanford who received various prizes such as INFORMS Nicholson Prize, Student Paper Competition, the INFORMS Computing Society Prize, the INFORMS Optimization Prize for Young Researchers. According to Google Scholar, his publications have been cited 52,000 times.

For Attendees' Attention

• Seating is on a first come, first served basis.