activity
20162026
most citedAn optimal algorithm for the Thresholding Bandit Problem

64 citations · 106 across the 5 of their papers we have counts for

collaborators

5 papers

stat.ML2026

Active multiple matrix completion with adaptive confidence sets

Andrea Locatelli, Alexandra Carpentier, Michal Valko

In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the l…

stat.ML2017★ 1 cited

An Adaptive Strategy for Active Learning with Smooth Decision Boundary

Andrea Locatelli, Alexandra Carpentier, Samory Kpotufe

We present the first adaptive strategy for active learning in the setting of classification with smooth decision boundary. The problem of adaptivity (to unknown distributional para…

stat.ML2017★ 4 cited

Adaptivity to Noise Parameters in Nonparametric Active Learning

Andrea Locatelli, Alexandra Carpentier, Samory Kpotufe

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish…

stat.ML2016★ 37 cited

Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem

Alexandra Carpentier, Andrea Locatelli

We consider the problem of \textit{best arm identification} with a \textit{fixed budget }, in the -armed stochastic bandit setting, with arms distribution defined on .…

stat.ML2016★ 64 cited

An optimal algorithm for the Thresholding Bandit Problem

Andrea Locatelli, Maurilio Gutzeit, Alexandra Carpentier

We study a specific \textit{combinatorial pure exploration stochastic bandit problem} where the learner aims at finding the set of arms whose means are above a given threshold, up…