Online Linear Optimization with Many Hints

Abstract

We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ "hint" vectors in each round prior to making a decision. In this setting, we devise an algorithm that obtains logarithmic regret whenever there exists a convex combination of the $K$ hints that has positive correlation with the cost vectors. This significantly extends prior work that considered only the case $K=1$. To accomplish this, we develop a way to combine many arbitrary OLO algorithms to obtain regret only a logarithmically worse factor than the minimum regret of the original algorithms in hindsight; this result is of independent interest.

arXiv commentAccepted at Neurips 2020

References in corpus (6)

• Online Learning with Predictable Sequences
• Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning
• Adaptive scale-invariant online algorithms for learning linear models
• Lipschitz and Comparator-Norm Adaptivity in Online Learning
• Online Learning with Imperfect Hints
• Matrix-Free Preconditioning in Online Learning