We improve the theoretical analysis and empirical performance of algorithms for the stochastic multi-armed bandit problem and the linear stochastic multi-armed bandit problem. In particular, we show that a simple modification of Auer’s UCB algorithm (Auer, 2002) achieves with high probability constant regret. More importantly, we modify and, consequently, improve the analysis of the algorithm f...

The multi-armed bandit is a concise model for the problem of iterated decision-making under uncertainty. In each round, a gambler must pull one of K arms of a slot machine, without any foreknowledge of their payouts, except that they are uniformly bounded. A standard objective is to minimize the gambler’s regret, de ned as the gambler’s total payout minus the largest payout which would have bee...

We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generative image segmentation algorithm for reliable multi-label segmentations in natural images. In contrast to most existing algorithms which focus on the inter-label discrimination, we address the problem of finding the generative model for e...

This paper studies active learning in the context of robust statistics. Specifically, we propose the Contaminated Best Arm Identification variant of the multi-armed bandit problem, in which every arm pull has probability ε of generating a sample from an arbitrary contamination distribution instead of the true underlying distribution. The goal is to identify the best (or approximately best) true...

We propose an easy-to-understand, visual performance model that offers insights to programmers and architects on improving parallel software and hardware for floating point computations.

This paper introduces a new algorithm to deal with multiobjective combinatorial and continuous problems. The algorithm is an extension of a previous one designed to deal with single objective combinatorial problems. The original purpose of the single objective version was to study in a rigorous way the properties the search graph of a particular problem needs to hold so that a randomized local ...

We study the multi-armed bandit problem with multiple plays and a budget constraint for both the stochastic and the adversarial setting. At each round, exactly K out of N possible arms have to be played (with 1 ≤ K ≤ N ). In addition to observing the individual rewards for each arm played, the player also learns a vector of costs which has to be covered with an a-priori defined budget B. The ga...

Computing the medoid of a large number of points in high-dimensional space is an increasingly common operation in many data science problems. We present an algorithm Med-dit which uses O(n log n) distance evaluations to compute the medoid with high probability. Med-dit is based on a connection with the multi-armed bandit problem. We evaluate the performance of Med-dit empirically on the Netflix...