Prediction with expert advice: a PDE perspective

DOI10.1007/s00332-019-09570-3zbMath1439.35484arXiv1904.11401OpenAlexW2940507394MaRDI QIDQ2303761

Robert V. Kohn, Nadejda Drenska

Publication date: 5 March 2020

Published in: Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1904.11401

zbMATH Keywords

dynamic programmingviscosity solutionsprediction with expert advicetwo-person gamesregret minimization

Mathematics Subject Classification ID

2-person games (91A05) Discrete-time games (91A50) Optimality conditions for minimax problems (49K35) Viscosity solutions to Hamilton-Jacobi equations in optimal control and differential games (49L25) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Viscosity solutions to PDEs (35D40) Robustness in mathematical programming (90C17)

Related Items (6)

Asymptotically optimal strategies for online prediction with history-dependent experts ⋮ Online Prediction with <scp>History‐Dependent</scp> Experts: The General Case ⋮ A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History‐Dependent Experts ⋮ Optimal anytime regret with two experts ⋮ Unnamed Item ⋮ Finite-time 4-expert prediction problem

Cites Work

• Unnamed Item
• Unnamed Item
• The obstacle problem for the \(p\)-Laplacian via optimal stopping of tug-of-war games
• Tug-of-war with noise: a game-theoretic view of the \(p\)-Laplacian
• The weighted majority algorithm
• Absolutely minimal Lipschitz extension of tree-valued mappings
• On the asymptotic optimality of the comb strategy for prediction with expert advice
• Tug-of-war and the infinity Laplacian
• A finite difference approach to the infinity Laplace equation and tug-of-war games
• A deterministic-control-based approach to fully nonlinear parabolic and elliptic equations
• User’s guide to viscosity solutions of second order partial differential equations
• Towards Optimal Algorithms for Prediction with Expert Advice
• Tug-of-War and Infinity Laplace Equation with Vanishing Neumann Boundary Condition
• A deterministic‐control‐based approach motion by curvature
• Prediction, Learning, and Games
• Convergent Difference Schemes for Degenerate Elliptic and Parabolic Equations: Hamilton--Jacobi Equations and Free Boundary Problems

This page was built for publication: Prediction with expert advice: a PDE perspective