A fundamental challenge in interactive learning and decision making, ranging from bandit
problems to reinforcement learning, is to provide sample-efficient, adaptive learning …

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved
performance on" easy" problems with a gap between the best and second-best arm. Are …

Active learning is perhaps most naturally posed as an online learning problem. However,
prior active learning approaches with deep neural networks assume offline access to the …

We consider the problem of contextual bandits and imitation learning, where the learner
lacks direct knowledge of the executed action's reward. Instead, the learner can actively …

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be
efficient in terms of statistical complexity, computational complexity, and query complexity. In …

Aligning large language models (LLM) with human preference plays a key role in building
modern generative models and can be achieved by reinforcement learning from human …

Data sampling methods have been investigated for decades in the context of machine
learning and statistical algorithms, with significant progress made in the past few years …

We design an active learning algorithm for cost-sensitive multiclass classification: problems
where different errors have different costs. Our algorithm, COAL, makes predictions by …

In this work, we investigate the expressiveness of the" conditional mutual information"(CMI)
framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a …

We present a minimax optimal learner for the problem of learning predictors robust to
adversarial examples at test-time. Interestingly, we find that this requires new algorithmic …