Search Results for author: Andrea Locatelli

Found 5 papers, 0 papers with code

An Adaptive Strategy for Active Learning with Smooth Decision Boundary

no code implementations25 Nov 2017 Andrea Locatelli, Alexandra Carpentier, Samory Kpotufe

The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro and Nowak (2007), which first established (active learning) rates for this setting.

Active Learning General Classification

Adaptivity to Noise Parameters in Nonparametric Active Learning

no code implementations16 Mar 2017 Andrea Locatelli, Alexandra Carpentier, Samory Kpotufe

This work addresses various open questions in the theory of active learning for nonparametric classification.

Active Learning General Classification

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

no code implementations29 May 2016 Alexandra Carpentier, Andrea Locatelli

We consider the problem of \textit{best arm identification} with a \textit{fixed budget $T$}, in the $K$-armed stochastic bandit setting, with arms distribution defined on $[0, 1]$.

An optimal algorithm for the Thresholding Bandit Problem

no code implementations27 May 2016 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 to a given precision, and \textit{for a fixed time horizon}.

Cannot find the paper you are looking for? You can Submit a new open access paper.