Search Results - "Garivier, Aurélien"

KULLBACK-LEIBLER UPPER CONFIDENCE BOUNDS FOR OPTIMAL SEQUENTIAL ALLOCATION by Cappé, Olivier, Garivier, Aurélien, Maillard, Odalric-Ambrym, Munos, Rémi, Stoltz, Gilles

“…We consider optimal sequential allocation in the context of the so-called stochastic multi-armed bandit model. We describe a generic index policy, in the sense…”
Get full text

Nonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit models by Garivier, Aurélien, Kaufmann, Emilie

“…In this article, we study sequential testing problems with overlapping hypotheses. We first focus on the simple problem of assessing if the mean μ of a…”
Get full text

A review on quantile regression for stochastic computer experiments by Torossian, Léonard, Picheny, Victor, Faivre, Robert, Garivier, Aurélien

“…•We review six quantile metamodels in a unified framework, highlighting similarities and differences.•The methods are analyzed through an extensive benchmark…”
Get full text

SEQUENTIAL MONTE CARLO SMOOTHING FOR GENERAL STATE SPACE HIDDEN MARKOV MODELS by Douc, Randal, Garivier, Aurélien, Moulines, Eric, Olsson, Jimmy

“…Computing smoothing distributions, the distributions of one or more states conditional on past, present, and future observations is a recurring problem when…”
Get full text

Perfect simulation of processes with long memory: A "coupling into and from the past" algorithm by Garivier, Aurélien

“…ABSTRACT We describe a new algorithm for the perfect simulation of variable length Markov chains and random systems with perfect connections. This algorithm,…”
Get full text

Hierarchical and Unsupervised Graph Representation Learning with Loukas’s Coarsening by Béthune, Louis, Kaloga, Yacouba, Borgnat, Pierre, Garivier, Aurélien, Habrard, Amaury

“…We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current…”
Get full text

Private Quantiles Estimation in the Presence of Atoms by Lalanne, Clément, Gastaud, Clément, Grislain, Nicolas, Garivier, Aurélien, Gribonval, Rémi

“…We consider the differentially private estimation of multiple quantiles (MQ) of a distribution from a dataset, a key building block in modern data analysis. We…”
Get full text

Conditional Quantile Sequential Estimation for Stochastic Codes by Labopin-Richard, Tatiana, Gamboa, Fabrice, Garivier, Aurélien, Stenger, Jérôme

“…We propose and analyze an algorithm for the sequential estimation of a conditional quantile in the context of real stochastic codes with vector-valued inputs…”
Get full text

A Lower-Bound for the Maximin Redundancy in Pattern Coding by Aurélien Garivier

“…We show that the maximin average redundancy in pattern coding is eventually larger than 1.84 (n/log n)1/3 for messages of length n. This improves recent…”
Get full text

Learning the distribution with largest mean: two bandit frameworks by Kaufmann, Emilie, Garivier, Aurélien

“…Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications…”
Get full text

Joint Estimation of Intersecting Context Tree Models by GALVES, ANTONIO, GARIVIER, AURÉLIEN, GASSIAT, ELISABETH

“…We study a problem of model selection for data produced by two different context tree sources. Motivated by linguistic questions, we consider the case where…”
Get full text

Consistency of the Unlimited BIC Context Tree Estimator by Garivier, A.

“…The Bayesian information criterion (BIC) and Krichevsky- Trofimov (KT) version of minimum description length (MDL) principle are popular in the study of model…”
Get full text

On Approximate Maximum-Likelihood Methods for Blind Identification: How to Cope With the Curse of Dimensionality by Barembruch, S., Garivier, A., Moulines, E.

“…We discuss approximate maximum-likelihood methods for blind identification and deconvolution. These algorithms are based on particle approximation versions of…”
Get full text

Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models by Garivier, Aurélien, Kaufmann, Emilie

“…In this paper, we study sequential testing problems with overlapping hypotheses. We first focus on the simple problem of assessing if the mean µ of a Gaussian…”
Get full text

Optimism in reinforcement learning and Kullback-Leibler divergence by Filippi, S, Cappé, Olivier, Garivier, Aurélien

“…We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can…”
Get full text

Optimally Sensing a Single Channel Without Prior Information: The Tiling Algorithm and Regret Bounds by Filippi, Sarah, Cappé, Olivier, Garivier, Aurélien

“…We consider the task of optimally sensing a two-state Markovian channel with an observation cost and without any prior information regarding the channel's…”
Get full text

About the Cost of Central Privacy in Density Estimation by Lalanne, Clément, Garivier, Aurélien, Gribonval, Rémi

“…We study non-parametric density estimation for densities in Lipschitz and Sobolev spaces, and under central privacy. In particular, we investigate regimes…”
Get full text

Foreword by Garivier, Aurélien

Get full text

Foreword by Garivier, Aurélien

Get full text

Foreword by Garivier, Aurélien, Garivier, Aurélien

Get full text