Monday, October 22

3108 Etcheverry Hall
3:30-4:30pm

 

Abstract: Randomization technique has been widely used in designing optimization algorithms to achieve properties that deterministic algorithms cannot do, such as SGD, BCD, ADMM, Reinforced Learning etc. In this talk, we use randomized ADMM to illustrate that too much randomness may be harmful to the algorithm convergence. Therefore, randomness needs to be carefully managed to take advantage of the technique, and we report computational experiences on this research direction.

Jointly with Kresimir Mihic and Mingxi Zhu.

Bio: Yinyu Ye is currently the Kwoh-Ting Li Professor in the School of Engineering at the Department of Management Science and Engineering and Institute of Computational and Mathematical Engineering and the Director of the MS&E Industrial Affiliates Program, Stanford University. He received the B.S. degree in System Engineering from the Huazhong University of Science and Technology, China, and the M.S. and Ph.D. degrees in Engineering-Economic Systems and Operations Research from Stanford University. Ye's research interests lie in the areas of optimization, complexity theory, algorithm design and analysis, and applications of mathematical programming, operations research and system engineering. He is also interested in developing optimization software for various real-world applications. Current research topics include Liner Programming Algorithms, Markov Decision Processes, Computational Game/Market Equilibrium, Metric Distance Geometry, Dynamic Resource Allocation, and Stochastic and Robust Decision Making, etc. He is an INFORMS (The Institute for Operations Research and The Management Science) Fellow, and has received several research awards including the winner of the 2014 SIAG/Optimization Prize awarded every three years to the author(s) of the most outstanding paper, the inaugural 2012 ISMP Tseng Lectureship Prize for outstanding contribution to continuous optimization, the 2009 John von Neumann Theory Prize for fundamental sustained contributions to theory in Operations Research and the Management Sciences, the inaugural 2006 Farkas prize on Optimization, and the 2009 IBM Faculty Award. He has supervised numerous doctoral students at Stanford who received received the 2015 and 2013 Second Prize of INFORMS Nicholson Student Paper Competition, the 2013 INFORMS Computing Society Prize, the 2008 Nicholson Prize, and the 2006 and 2010 INFORMS Optimization Prizes for Young Researchers. Ye teaches courses on Optimization, Network and Integer Programming, Semidefinite Programming, etc. He has written extensively on Interior-Point Methods, Approximation Algorithms, Conic Optimization, and their applications; and served as a consultant or technical board member to a variety of industries, including MOSEK.

Wednesday, October 24

3110 Etcheverry Hall

12:00-2:00pm

BxB Digital, a Brambles company, is hiring full time positions and internships. Join us next week to learn how you can work with our innovative team of engineers. Lunch will be included. 
At BxB Digital, technology and data intelligence come together. We combine network concepts, enterprise supply chain expertise, machine learning and the Internet of Things (IoT) to provide transparency throughout the supply chain. 

Facebook Event: https://www.facebook.com/events/251783532201623/
 

Technical Product 
- Manager/Intern

Embedded Systems
- Intern

Hardware Design
- Intern

IoT Technical Programs
- Manager (Full-time)

Electronics Manufacturing & Sourcing
- Manager (Full-time)

 

Monday, October 29

3108 Etcheverry Hall
3:30-4:30pm

Abstract – Traditionally, Stochastic Optimization deals with optimization models in which some of the data is modeled using random variables. In contrast, Learning Models are intended to capture the behavior of covariates, where the goal is to characterize the behavior of the response (random variable) to the predictors (random variables).  The field of Statistical (or Machine) Learning focuses on understanding these relationships.  The goal of this talk is to present a new class of composite optimization models in which the learning and optimization models live symbiotically.  We will discuss several examples of such problems, and how they give rise to a rich class of problems.  (This talk is based on the work of several Ph.D. students, and in particular Yunxiao Deng, Junyi Liu and Shuotao Diao).

Bio: Professor Sen served as a program director at NSF where he was responsible for the Operations Research, and the Service Enterprise Engineering programs. At NSF, he also headed the Cyber infrastructure planning activities of the Engineering Directorate. Concurrently with his appointment at NSF, he was a professor of Systems and Industrial Engineering at the University of Arizona.

Professor Sen has served on the editorial board of several journals, including Operations Research as Area Editor for Optimization, and as Associate Editor in INFORMS Journal on Computing, Telecommunications Systems, as well as Operations Research. He is the past-Chair of the INFORMS Telecommunications Section and founded the INFORMS Optimization Section. Professor Sen is a Fellow of INFORMS. 

Monday, November 19

3108 Etcheverry Hall
3:30-4:30pm

Bio: Roger Wets is a Distinguished Research Professor of Mathematics at the University of California, Davis. He guided nineteen students to their Ph.D. His main research interests have been stochastic optimization and variational analysis. For this work he has received a number of prizes that include Guggenheim and Erskine Fellowships, the SIAM-MPS Dantzig Prize in Mathematical programming and the INFORMS Lanchester prize for the book “Variational Analysis” that he co-authored with R.T. Rockafellar. During the last decade his research has been focused on equilibrium problems, in particular equilibrium problems in a stochastic environment, and on nonparametric estimation, in particular on the fusion of hard and soft information. Over time, he has been associated with the Boeing Scientific Research Labs, the International Institute of Applied Systems Analysis (Laxenburg, Austria), the IBM-T.J. Watson Research Center (Yorktown Heights, N.Y.), the Center for Mathematical Modeling of the University of Chile and the World Bank. This resulted in getting involved in projects related to aerospace, telecommunications, finance, soil management and water resources, manufacturing and energy. He has published about 200 technical articles, mostly in pure and applied mathematical journals, but also in journals dealing with probability, statistics, economics and ecology. He held, or holds, editorial positions on a number of leading journals in mathematics and operations research.

Monday, November 26

3108 Etcheverry Hall
3:30-4:30pm

Department of Chemical and Biomolecular Engineering, University of California Berkeley

Abstract: Traditional sample-based uncertainty propagation methods are generally computationally expensive for online optimization applications. In this talk, we will discuss arbitrary polynomial chaos (aPC) for quantification of probabilistic uncertainties with arbitrary measures (e.g., uncertainties with correlated multivariate or multi-modal distributions). aPC can be used as an efficient uncertainty propagation method for optimization-based analysis, estimation, and control of nonlinear systems with probabilistic uncertainties In particular, we will demonstrate the use of aPC for the design and performance verification of model predictive control (MPC) for stochastic nonlinear systems.

Research interests: Our research lies at the intersection of control theory, applied mathematics, and process systems engineering. The main thrust of our theoretical research is to develop novel systems analysis techniques and application-relevant control theory for complex dynamical systems that are stochastic and nonlinear. The systems analysis and control theory developments are intended to (i) improve our fundamental understanding of complex chemical and biological systems in order to answer specific questions related to underlying physicochemical or biological mechanisms of a system, and (ii) enable high-performance and cost-effective control of complex systems using physics-based knowledge of their dynamics. Our multidisciplinary research efforts provide a balance between theory, computation, and real-word applications, with a particular emphasis on energy and life science applications.