3 papers
cs.LG2026
Optimal Learning Under Tsybakov Noise
Steve Hanneke, Hongao Wang, Mingyue Xu
Probably Approximately Correct (PAC) learning [Val84] is a fundamental learning model that has been extensively investigated. In this model, $\mathcal{H} \subseteq \{0,1\}^{\mathca…
cs.LG2026
Universal Multiclass Transductive Online Learning
Steve Hanneke, Hongao Wang
We consider the problem of universal transductive online classification with a possibly unbounded label space. This setting considers online learning, with the sequence of instance…
stat.ML2025
A Theory of Optimistically Universal Online Learnability for General Concept Classes
Steve Hanneke, Hongao Wang
We provide a full characterization of the concept classes that are optimistically universally online learnable with labels. The notion of optimistically universal online…