Statistics

We present GL-LowPopArt, a novel Catoni-style estimator for generalized low-rank trace regression. Building on LowPopArt (Jang et al., …

We study the problem of clustering T trajectories of length H, each generated by one of K unknown ergodic Markov chains over a finite …

Active learning improves training efficiency by selectively querying the most informative samples for labeling. While it naturally fits …

We consider the problem of contextual online RLHF with general preferences, where the goal is to identify the Nash Equilibrium. We …

We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes various …

We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is …

Proposes a new active learning approach by proposing a new uncertainty measure called the least disagree metric, as well as its efficient estimator, which is proven to be asymptotically consistent. This is then combined with seeding to become a new active learning algorith, LDM-S, which is shown to outperform existing approaches across various architectures and datasets.

Logistic bandit is a ubiquitous framework of modeling users’ choices, e.g., click vs. no click for advertisement recommender …

Proposes a framework for performing fair PCA in memory limited, streaming setting. Sample complexity results and empirical discussions show the superiority of our approach compared to the existing approaches.

First theoretical analysis of model estimation and reward-free RL of block MDP, without resorting to function approximation frameworks. Lower bounds and algorithms with near-optimal upper bound are provided.