Skip to content
conftrace_
2025 ALT ALT 2025

For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Steve Hanneke, Amirreza Shaeiri, Hongao Wang

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Mathematics & Optimization > Mathematics > Probability

Keywords

bandit feedback agnostic setting realizable setting universal learnability littlestone tree multiclass online learning
Download PDF