Finite-Time 4-Expert Prediction Problem

DOI10.1080/03605302.2020.1712418MaRDI QIDQ6329824arXivFDO

Authors Erhan Bayraktar, Ibrahim Ekren, Xin Zhang

Publication date 21 November 2019

Published in arXiv

Full work available at URL https://doi.org/10.1080/03605302.2020.1712418

Mathematics Subject Classification ID

Nonlinear parabolic equations (35K55) Degenerate parabolic equations (35K65) PDEs in connection with computer science (35Q68) Dynamic programming in optimal control and differential games (49L20) Numerical mathematical programming methods (65K05) Learning and adaptive systems in artificial intelligence (68T05) Applications of game theory (91A80)

arXiv classification

cs.GTcs.LGmath.APmath.PRstat.ML

Abstract: We explicitly solve the nonlinear PDE that is the continuous limit of dynamic programming of emph{expert prediction problem} in finite horizon setting with $N=4$ experts. The emph{expert prediction problem} is formulated as a zero sum game between a player and an adversary. By showing that the solution is $mathcal{C}^2$, we are able to show that the strategies conjectured in arXiv:1409.3040G form an asymptotic Nash equilibrium. We also prove the "Finite vs Geometric regret" conjecture proposed in arXiv:1409.3040G for $N=4$, and and show that this conjecture in fact follows from the conjecture that the comb strategies are optimal.

This page was built for publication: Finite-Time 4-Expert Prediction Problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6329824)