English

Finite-Time 4-Expert Prediction Problem

Probability 2019-12-04 v2 Computer Science and Game Theory Machine Learning Analysis of PDEs Machine Learning

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=4N=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 C2\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=4N=4, and and show that this conjecture in fact follows from the conjecture that the comb strategies are optimal.

Keywords

Cite

@article{arxiv.1911.10936,
  title  = {Finite-Time 4-Expert Prediction Problem},
  author = {Erhan Bayraktar and Ibrahim Ekren and Xin Zhang},
  journal= {arXiv preprint arXiv:1911.10936},
  year   = {2019}
}

Comments

Keywords: machine learning, expert advice framework, asymptotic expansion, inverse Laplace transform, regret minimization, Jacobi-theta function

R2 v1 2026-06-23T12:26:24.563Z