6 accepted papers
The minimax sample complexity of group distributionally robust optimization (GDRO) has been determined up to a $\log(K)$ factor, where $K$ is the number of groups. In this work, we venture beyond the minimax perspective via a novel notion of sparsity that we call $(\lambda, \beta)$-sparsity. In shor…
We introduce the thresholded linear bandit problem, a novel sequential decision making problem at the interface of structured stochastic multi-armed bandits and learning halfspaces. The set of arms is $[0, 1]^d$, the expected Bernoulli reward is piecewise constant with a jump at a separating hyperpl…
Much of the work in online learning focuses on the study of sublinear upper bounds on the regret. In this work, we initiate the study of best-case lower bounds in online convex optimization, wherein we bound the largest \emph{improvement} an algorithm can obtain relative to the single best action in…
We study a variant of decision-theoretic online learning in which the set of experts that are available to Learner can shrink over time. This is a restricted version of the well-studied sleeping experts problem, itself a generalization of the fundamental game of prediction with expert advice. Simila…
Given a data set of $(x,y)$ pairs, a common learning task is to fit a model predicting $y$ (a label or dependent variable) conditioned on $x$. This paper considers the similar but much less-understood problem of modeling “higher-order” statistics of $y$’s distribution conditioned on $x$. Such statis…
This paper addresses the stochastic multi-armed bandit problem with an undirected feedback graph. We devise a UCB-based algorithm, UCB-NE, to provide a problem-dependent regret bound that depends on a clique covering. Our algorithm obtains regret which provably scales linearly with the clique coveri…