We give novel algorithms for multi-task and lifelong linear bandits with shared
representation. Specifically, we consider the setting where we play $ M $ linear bandits with …

Bandit problems with linear or concave reward have been extensively studied, but relatively
few works have studied bandits with non-concave reward. This work considers a large family …

We consider a contextual bandit problem with $ S $ contexts and $ K $ actions. In each
round $ t= 1, 2,\dots $ the learnerobserves a random context and chooses an action based …

Despite the recent success of representation learning in sequential decision making, the
study of the pure exploration scenario (ie, identify the best option and minimize the sample …

We initiate the study of tradeoffs between exploration and exploitation in online learning of
properties of quantum states. Given sequential oracle access to an unknown quantum state …

Assuming distributions are Gaussian often facilitates computations that are otherwise
intractable. We study the performance of an agent that attains a bounded information ratio …

In stochastic zeroth-order optimization, a problem of practical relevance is understanding
how to fully exploit the local geometry of the underlying objective function. We consider a …

Statistical complexity and optimal algorithms for nonlinear ridge bandits Page 1 The Annals of
Statistics 2024, Vol. 52, No. 6, 2557–2582 https://doi.org/10.1214/24-AOS2395 © Institute of …

Optimization of smooth reward functions under bandit feedback is a long-standing problem
in online learning. This paper approaches this problem by studying the convergence under …

Recent progress in robust statistical learning has mainly tackled convex problems, like mean
estimation or linear regression, with non-convex challenges receiving less attention. Phase …