On the asymptotic optimality of the comb strategy for prediction with expert advice

DOI10.1214/20-AAP1565MaRDI QIDQ2240467

Erhan Bayraktar, Ibrahim Ekren, Yi-li Zhang

Publication date: 4 November 2021

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.02368

zbMATH Keywords

asymptotic expansionmachine learningreflected Brownian motionregret minimizationsystem of hyperbolic equationsexpert advice framework

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonlinear elliptic equations (35J60) First-order hyperbolic equations (35L02)

Related Items (5)

Asymptotically optimal strategies for online prediction with history-dependent experts ⋮ Online Prediction with <scp>History‐Dependent</scp> Experts: The General Case ⋮ Optimal anytime regret with two experts ⋮ Unnamed Item ⋮ Prediction with expert advice: a PDE perspective

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The weighted majority algorithm
• Planar diffusions with rank-based characteristics and perturbed Tanaka equations
• Strong solutions of stochastic equations with rank-based coefficients
• UTILITY MAXIMIZATION UNDER MODEL UNCERTAINTY IN DISCRETE TIME
• Robust Feedback Switching Control: Dynamic Programming and Viscosity Solutions
• Two Person Zero-Sum Game in Weak Formulation and Path Dependent Bellman--Isaacs Equation
• A deterministic-control-based approach to fully nonlinear parabolic and elliptic equations
• User’s guide to viscosity solutions of second order partial differential equations
• A method for finding exact solutions to hyperbolic systems of first-order PDEs
• Towards Optimal Algorithms for Prediction with Expert Advice
• Stochastic Perron's Method for Hamilton--Jacobi--Bellman Equations
• Prediction, Learning, and Games

This page was built for publication: On the asymptotic optimality of the comb strategy for prediction with expert advice