Vianney Perchet

research

∙ 09/01/2023

Local and adaptive mirror descents in extensive-form games

We study how to learn ϵ-optimal strategies in zero-sum imperfect informa...

0 Côme Fiegel, et al. ∙

research

∙ 06/23/2023

Trading-off price for data quality to achieve fair online allocation

We consider the problem of online allocation subject to a long-term fair...

0 Mathieu Molina, et al. ∙

research

∙ 06/13/2023

Online Matching in Geometric Random Graphs

In online advertisement, ad campaigns are sequentially displayed to user...

0 Flore Sentenac, et al. ∙

research

∙ 06/03/2023

DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation

Many machine learning problems require performing dataset valuation, i.e...

0 Felipe Garrido-Lucero, et al. ∙

research

∙ 03/16/2023

Addressing bias in online selection with limited budget of comparisons

Consider a hiring process with candidates coming from different universi...

0 Ziyad Benomar, et al. ∙

research

∙ 12/23/2022

Adapting to game trees in zero-sum imperfect information games

Imperfect information games (IIG) are games in which each player only pa...

0 Côme Fiegel, et al. ∙

research

∙ 11/29/2022

A survey on multi-player bandits

Due mostly to its application to cognitive radio networks, multiplayer b...

0 Etienne Boursier, et al. ∙

research

∙ 10/23/2022

Stochastic Mirror Descent for Large-Scale Sparse Recovery

In this paper we discuss an application of Stochastic Approximation to s...

0 Sasila Ilandarideva, et al. ∙

research

∙ 05/26/2022

Active Labeling: Streaming Stochastic Gradients

The workhorse of machine learning is stochastic gradient descent. To acc...

0 Vivien Cabannes, et al. ∙

research

∙ 02/15/2022

An algorithmic solution to the Blotto game using multi-marginal couplings

We describe an efficient algorithm to compute solutions for the general ...

0 Vianney Perchet, et al. ∙

research

∙ 12/11/2021

Privacy Amplification via Shuffling for Linear Contextual Bandits

Contextual bandit algorithms are widely used in domains where it is desi...

0 Evrard Garcelon, et al. ∙

research

∙ 11/02/2021

Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge

We consider the problem of online linear regression in the stochastic se...

7 Reda Ouhamma, et al. ∙

research

∙ 10/18/2021

Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits

In the fixed budget thresholding bandit problem, an algorithm sequential...

9 Reda Ouhamma, et al. ∙

research

∙ 07/31/2021

Pure Exploration and Regret Minimization in Matching Bandits

Finding an optimal matching in a weighted graph is a standard combinator...

4 Flore Sentenac, et al. ∙

research

∙ 07/02/2021

Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm

Motivated by sequential budgeted allocation problems, we investigate onl...

0 Nathan Noiry, et al. ∙

research

∙ 06/10/2021

Unsupervised Neural Hidden Markov Models with a Continuous latent state space

We introduce a new procedure to neuralize unsupervised Hidden Markov Mod...

0 Firas Jarboui, et al. ∙

research

∙ 06/09/2021

Offline Inverse Reinforcement Learning

The objective of offline RL is to learn optimal policies when a fixed ex...

0 Firas Jarboui, et al. ∙

research

∙ 06/08/2021

Decentralized Learning in Online Queuing Systems

Motivated by packet routing in computer networks, online queuing systems...

0 Flore Sentenac, et al. ∙

research

∙ 05/25/2021

A Generalised Inverse Reinforcement Learning Framework

The gloabal objective of inverse Reinforcement Learning (IRL) is to esti...

0 Firas Jarboui, et al. ∙

research

∙ 03/17/2021

Homomorphically Encrypted Linear Contextual Bandit

Contextual bandit is a general framework for online learning in sequenti...

0 Evrard Garcelon, et al. ∙

research

∙ 02/16/2021

Making the most of your day: online learning for optimal allocation of time

We study online learning for optimal allocation when the resource to be ...

0 Etienne Boursier, et al. ∙

research

∙ 01/04/2021

Be Greedy in Multi-Armed Bandits

The Greedy algorithm is the simplest heuristic in sequential decision pr...

0 Matthieu Jedor, et al. ∙

research

∙ 12/28/2020

Lifelong Learning in Multi-Armed Bandits

Continuously learning and leveraging the knowledge accumulated from prio...

0 Matthieu Jedor, et al. ∙

research

∙ 11/18/2020

Learning in repeated auctions

Auction theory historically focused on the question of designing the bes...

0 Thomas Nedelec, et al. ∙

research

∙ 11/09/2020

Robustness of Community Detection to Random Geometric Perturbations

We consider the stochastic block model where connection between vertices...

0 Sandrine Péché, et al. ∙

research

∙ 10/15/2020

Local Differentially Private Regret Minimization in Reinforcement Learning

Reinforcement learning algorithms are widely used in domains where it is...

0 Evrard Garcelon, et al. ∙

research

∙ 07/20/2020

Speed of Social Learning from Reviews in Non-Stationary Environments

Potential buyers of a product or service tend to first browse feedback f...

0 Etienne Boursier, et al. ∙

research

∙ 06/11/2020

Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits

We investigate stochastic combinatorial multi-armed bandit with semi-ban...

0 Pierre Perrault, et al. ∙

research

∙ 05/04/2020

Categorized Bandits

We introduce a new stochastic multi-armed bandit setting where arms are ...

0 Matthieu Jedor, et al. ∙

research

∙ 02/04/2020

Selfish Robustness and Equilibria in Multi-Player Bandits

Motivated by cognitive radios, stochastic multi-player multi-armed bandi...

0 Etienne Boursier, et al. ∙

research

∙ 09/15/2019

Adversarial learning for revenue-maximizing auctions

We introduce a new numerical framework to learn optimal bidding strategi...

0 Thomas Nedelec, et al. ∙

research

∙ 07/10/2019

Markov Decision Process for MOOC users behavioral inference

Studies on massive open online courses (MOOCs) users discuss the existen...

0 Firas Jarboui, et al. ∙

research

∙ 06/20/2019

Active Linear Regression

We consider the problem of active linear regression where a decision mak...

0 Xavier Fontaine, et al. ∙

research

∙ 05/29/2019

Robust Stackelberg buyers in repeated auctions

We consider the practical and classical setting where the seller is usin...

0 Clément Calauzènes, et al. ∙

research

∙ 05/28/2019

Repeated A/B Testing

We study a setting in which a learner faces a sequence of A/B tests and ...

0 Nicolò Cesa-Bianchi, et al. ∙

research

∙ 05/27/2019

Private Learning and Regularized Optimal Transport

Private data are valuable either by remaining private (for instance if t...

0 Etienne Boursier, et al. ∙

research

∙ 02/27/2019

Learning to bid in revenue-maximizing auctions

We consider the problem of the optimization of bidding strategies in pri...

0 Thomas Nedelec, et al. ∙

research

∙ 02/12/2019

A Problem-Adaptive Algorithm for Resource Allocation

We consider a sequential stochastic resource allocation problem under th...

0 Xavier Fontaine, et al. ∙

research

∙ 02/11/2019

Exploiting Structure of Uncertainty for Efficient Combinatorial Semi-Bandits

We improve the efficiency of algorithms for stochastic combinatorial sem...

0 Pierre Perrault, et al. ∙

research

∙ 11/12/2018

A differential game on Wasserstein space. Application to weak approachability with partial monitoring

Studying continuous time counterpart of some discrete time dynamics is n...

0 Vianney Perchet, et al. ∙

research

∙ 10/11/2018

Regularized Contextual Bandits

We consider the stochastic contextual bandit problem with additional reg...

0 Xavier Fontaine, et al. ∙

research

∙ 10/09/2018

Bridging the gap between regret minimization and best arm identification, with application to A/B tests

State of the art online learning procedures focus either on selecting th...

0 Rémy Degenne, et al. ∙

research

∙ 09/21/2018

SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits

We consider the stochastic multiplayer multi-armed bandit problem, where...

0 Etienne Boursier, et al. ∙

research

∙ 08/21/2018

Thresholding the virtual value: a simple method to increase welfare and lower reserve prices in online auction systems

Second price auctions with reserve price are widely used by the main Int...

0 Thomas Nedelec, et al. ∙

research

∙ 07/10/2018

Bandits with Side Observations: Bounded vs. Logarithmic Regret

We consider the classical stochastic multi-armed bandit but where, from ...

0 Rémy Degenne, et al. ∙

research

∙ 07/09/2018

Dynamic Pricing with Finitely Many Unknown Valuations

Motivated by posted price auctions where buyers are grouped in an unknow...

0 Nicolò Cesa-Bianchi, et al. ∙

research

∙ 06/06/2018

Finding the Bandit in a Graph: Sequential Search-and-Stop

We consider the problem where an agent wants to find a hidden object tha...

0 Pierre Perrault, et al. ∙

research

∙ 05/01/2018

Explicit shading strategies for repeated truthful auctions

With the increasing use of auctions in online advertising, there has bee...

0 Marc Abeille, et al. ∙

research

∙ 04/03/2017

A comparative study of counterfactual estimators

We provide a comparative study of several widely used off-policy estimat...

0 Thomas Nedelec, et al. ∙

research

∙ 02/22/2017

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

We consider the problem of bandit optimization, inspired by stochastic o...

0 Quentin Berthet, et al. ∙

Vianney Perchet

Featured Co-authors