We study a new risk-averse bandit setting motivated by semiconductor manufacturing, where the quality of a recipe is judged not by its mean performance but by its weakest outcomes. …
We revisit regularized regret minimization under full-information and bandit feedback, where a learner optimizes an objective of the form $\langle r, \pi \rangle - \eta^{-1} …
We present GL-LowPopArt, a novel Catoni-style estimator for generalized low-rank trace regression. Building on LowPopArt (Jang et al., 2024), it employs a two-stage approach -- …
We consider the problem of *regularized* best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized …
We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes various stochastic contextual bandit settings, including …
We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is guaranteed to be convex and numerically tight. …
Logistic bandit is a ubiquitous framework of modeling users' choices, e.g., click vs. no click for advertisement recommender system. We observe that the prior works overlook or …
A novel problem setting where heterogeneous multi-agent bandits collaborate over a network to minimize their group regret. To deal with the high communication complexity of the …