University of Connecticut

Events Calendar


Control And Optimization Seminar
Expert Prediction Problem
Xin Zhang (University Of Vienna)

Monday, November 29, 2021
2:00pm – 3:00pm

Storrs Campus
Online

Abstract: This talk focuses on expert prediction problem with finite horizon, which is formulated as a zero sum game between a player and an adversary. By considering a scaled game, the value function of discrete games converges to the viscosity solution of a PDE. We explicitly solve this nonlinear PDE with N = 4 experts. By showing that the solution is C^2, we are able to show that the comb strategies, as conjectured in “Towards Optimal Algorithms for Prediction with Expert Advice” by Peres et al., form an asymptotic Nash equilibrium. We also prove the “Finite vs Geometric regret” conjecture proposed in Peres et al. for N = 4, and show that this conjecture in fact follows from the conjecture that the comb strategies are optimal. This talk is based on a joint work with Erhan Bayraktar and Ibrahim Ekren.

Webex meeting link: https://uconn-cmr.webex.com/uconn-cmr/j.php?MTID=m0e001a40b4f4c4e435299d38b02df9e0 Meeting number: 2622 896 7255 Password: UConn

Speaker's short bio: Xin is currently a University Assistant at the University of Vienna. He obtained his Ph.D. from the University of Michigan in 2021. His research interests include probability, stochastic analysis, mean field game, optimal transport, and online learning. Please visit his website for more information: https://sites.google.com/umich.edu/xzhang/home

Contact:

bin.zou@uconn.edu (Bin Zou)

Control and Optimization (primary), UConn Master Calendar

Control Panel