SUNMONTUEWEDTHUFRISAT
Events for October 08, 2009
-
Reinforcement Learning and Markov Chain Computations, Part II
Thu, Oct 08, 2009 @ 02:00 PM - 03:00 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
University Calendar
Speaker: Prof. Vivek Borkar, Tata Institute of Fundamental Research (TIFR), Mumbai, IndiaPart I: Tuesday, Oct. 6, 2-3PM, HED 116Part II: Thursday, Oct. 8, 2-3PM, EEB 248This two part series shall cover an introduction to reinforcement learning and stochastic approximations, and its application to Markov Chain computations.Part I (Tuesday, Oct. 6) shall highlight the main strands in the reinforcement learning based approaches to approximate dynamic programming for Markov decision processes. In particular, connections to numerical methods for MDPs and convergence issues will be discussed.Part II (Thursday, Oct. 8) will present a novel potential application of reinforcement learning algorithms, viz., for certain matrix computations. It will be argued that these present a hybrid scheme situated between pure Monte Carlo and pure numerical iterative schemes. Various trade-offs and acceleration techniques will be discussed.Speaker Bio: Vivek Borkar is a Professor in the School of Technology and Computer Science at the Tata Institute of Fundamental Research (TIFR), Mumbai, where he has been for the last decade. He was formerly Dean of the same school. Prior to TIFR, he was a Professor in the Computer Science and Automation department of the Indian Institute of Science, Bangalore. He received his Ph.D. from University of California, Berkeley in EECS in 1979. He is well-known for his work in many areas including stochastic processes, mathematical control, game theory and learning. He is the author of several books including a recent book on Stochastic approximations: A Dynamical Systems Viewpoint.Host: Prof. Rahul Jain, 213-740-2246, rahul.jain@usc.edu.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Georgia Lum
-
On the Complexity of Game, Market, and Network Equilibria
Thu, Oct 08, 2009 @ 03:30 PM - 04:45 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
University Calendar
Daniel J. Epstein Department of Industrial and Systems Engineering ISE 650 Seminar:"On the Complexity of Game, Market, and Network Equilibria"SHANG-HUA TENG, Seeley G. Mudd Professor Computer Science Department, USC Viterbi School of EngineeringTHURSDAY, OCTOBER 8, 2009, 3:30PM - 4:45PM, ANDRUS GERONTOLOGY AUDITORIUMABSTRACT: I will present some recent advances in Algorithmic Game Theory. I will focus on the computational equivalence of Nash equilibria for games, Arrow-Debreu equilibria and Fisher equilibria for markets, and fractional equilibria for networks. In additional to worst-case complexity, I will consider the smoothed and approximation complexity of these problems. If time permits, I will highlight some potential computational difference between solution concepts in games and in multi-objective optimization. Joint work with Xi Chen, Xiaotie Deng, Deichen Dai, Ye Du, Li-Sha Huang, Shiva Kintali, Laura Poplawski, Rajmohan Rajaraman, Heiko Röglin, Ravi Sundaram and Paul Valiant.SHANG-HUA TENG is the Seeley G. Mudd Professor and Chair of the Computer Science Department at the USC Viterbi School of Engineering. He has taught as a faculty member in the Department of Mathematics of MIT and in the Computer Science Departments of Boston University, the University of Minnesota and UIUC. He has worked and consulted for Microsoft Research, Akamai, IBM Almaden Research Center, Intel Corporation, Xerox PARC, Cray Research/SGI, Thinking Machine Corporation, and the NASA Ames Research Center. He received dual B.S. degrees in computer science and in electrical engineering from Shanghai Jiao Tong University in 1985, an M.S. degree in computer science from USC in 1988, and a Ph.D. degree in computer science from Carnegie Mellon University in 1991.He is a recipient of the 2009 Fulkerson Prize (AMS-MPS) and the 2008 Gödel Prize (ACM-EATCS) for his joint work on Smoothed Analysis of Algorithms with Daniel Spielman. He is also an Alfred P. Sloan Fellow, a winner of the Senior Xerox Award for Outstanding Faculty Research (UIUC), and a recipient of the NSF Faculty Early Career Development Award. His recent research interests include computational game and economics theory, spectral graph theory, scientific computing, and mathematical programming. He has received more than ten US Patents for his work on compiler optimization and Internet technology.Hosted by Profs. Elaine Chew and Fernando Ordonez.
Location: Ethel Percy Andrus Gerontology Center (GER) - Auditorium
Audiences: Everyone Is Invited
Contact: Georgia Lum
-
USC Student Health Council Alumni Panel
Thu, Oct 08, 2009 @ 05:30 PM - 07:00 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
University Calendar
Thursday, October 8, 2009, 5:30-6:30 pm, followed by a 30 minute networking opportunityLocation TBDPatsy Rincon, Sr. Associate Consultant, Kaiser PermanenteNatalia Rincon, Project Manager, Regional Operations, HealthCare PartnersElizabeth Navarro, Valley Presbyterian HospitalPrub Khurana, VP of Strategy and Planning, Facey Medical Group Guests will be sharing their experience, knowledge relating to residencies, job search, and people skills.RSVP to https://usc.qualtrics.com/SE/?SID=SV_aaefjPszEVpCsXG&SVID=Prod by October 6 for the location.
Location: To Be Determined
Audiences: Everyone Is Invited
Contact: Georgia Lum
