activity
20122021
most citedSimple regret for infinitely many armed bandits

31 citations · 85 across the 11 of their papers we have counts for

collaborators
Showing stat.MLShow all

13 papers · 1 filter

stat.ML20211 cited

Problem Dependent View on Structured Thresholding Bandit Problems

James Cheshire, Pierre Ménard, Alexandra Carpentier

We investigate the problem dependent regime in the stochastic Thresholding Bandit problem (TBP) under several shape constraints. In the TBP, the objective of the learner is to outp…

stat.ML20211 cited

Generalized non-stationary bandits

Anne Gael Manegueu, Alexandra Carpentier, Yi Yu

In this paper, we study a non-stationary stochastic bandit problem, which generalizes the switching bandit problem. On top of the switching bandit problem (\textbf{Case a}), we are…

stat.ML2020

The Elliptical Potential Lemma Revisited

Alexandra Carpentier, Claire Vernade, Yasin Abbasi-Yadkori

This note proposes a new proof and new perspectives on the so-called Elliptical Potential Lemma. This result is important in online learning, especially for linear stochastic bandi…

stat.ML202012 cited

Stochastic bandits with arm-dependent delays

Anne Gael Manegueu, Claire Vernade, Alexandra Carpentier +1

Significant work has been recently dedicated to the stochastic delayed bandit setting because of its relevance in applications. The applicability of existing algorithms is however…

stat.ML2019

Restless dependent bandits with fading memory

Oleksandr Zadorozhnyi, Gilles Blanchard, Alexandra Carpentier

We study the stochastic multi-armed bandit problem in the case when the arm samples are dependent over time and generated from so-called weak $\cC$-mixing processes. We establish a…

stat.ML2018

A minimax near-optimal algorithm for adaptive rejection sampling

Juliette Achdou, Joseph C. Lam, Alexandra Carpentier +1

Rejection Sampling is a fundamental Monte-Carlo method. It is used to sample from distributions admitting a probability density function which can be evaluated exactly at any given…