1 citations · 1 across the 10 of their papers we have counts for
10 papers
Adversarially Robust PAC Learning with Optimal VC Rates
Steve Hanneke, Amirreza Shaeiri
We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distribution over $\mathcal{X} \times…
Towards a theory of inference-time alignment with unknown rewards
Steve Hanneke, Hongao Wang, Mingyue Xu
Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation. Yet, alignment has remained…
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…
Universal rates of ERM for agnostic learning
Steve Hanneke, Mingyue Xu
The universal learning framework has been developed to obtain guarantees on the learning rates that hold for any fixed distribution, which can be much faster than the ones uniforml…
Universal Rates of Empirical Risk Minimization
Steve Hanneke, Mingyue Xu
The well-known empirical risk minimization (ERM) principle is the basis of many widely used machine learning algorithms, and plays an essential role in the classical PAC theory. A…
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…
Multiclass Transductive Online Learning
Steve Hanneke, Vinod Raman, Amirreza Shaeiri +1
We consider the problem of multiclass transductive online learning when the number of labels can be unbounded. Previous works by Ben-David et al. [1997] and Hanneke et al. [2023b]…
Adversarial Rewards in Universal Learning for Contextual Bandits
Moise Blanchard, Steve Hanneke, Patrick Jaillet
We study the fundamental limits of learning in contextual bandits, where a learner's rewards depend on their actions and a known context, which extends the canonical multi-armed ba…
Contextual Bandits and Optimistically Universal Learning
Moise Blanchard, Steve Hanneke, Patrick Jaillet
We consider the contextual bandit problem on general action and context spaces, where the learner's rewards depend on their selected actions and an observable context. This general…
Universal Online Learning with Unbounded Losses: Memory Is All You Need
Moise Blanchard, Romain Cosson, Steve Hanneke
We resolve an open problem of Hanneke on the subject of universally consistent online learning with non-i.i.d. processes and unbounded losses. The notion of an optimistically unive…