Online Learning with an Almost Perfect Expert
Simina Br\^anzei, Yuval Peres

TL;DR
This paper analyzes the multiclass online learning problem, demonstrating that when the best expert makes very few mistakes, the forecaster's expected mistakes are tightly bounded, especially in binary prediction scenarios.
Contribution
It provides a tight bound on the expected mistakes of the optimal forecaster when the best expert makes few errors, extending understanding of online learning with expert advice.
Findings
Expected mistakes are at most log_4 n + o(log_4 n) when the best expert makes o(log_4 n) mistakes.
The bound is tight, with adversary strategies showing worst-case scenarios in binary prediction.
The analysis applies to the regime where the best expert's mistakes are very small relative to the number of experts.
Abstract
We study the multiclass online learning problem where a forecaster makes a sequence of predictions using the advice of experts. Our main contribution is to analyze the regime where the best expert makes at most mistakes and to show that when , the expected number of mistakes made by the optimal forecaster is at most . We also describe an adversary strategy showing that this bound is tight and that the worst case is attained for binary prediction.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Advanced Bandit Algorithms Research · Optimization and Search Problems
