298 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université de LilleFR364 papers
- Centre National de la Recherche ScientifiqueFR257 papers
- École Centrale de LilleFR212 papers
- Centre de Recherche en InformatiqueFR203 papers
- Université Paris-SaclayFR74 papers
- Institut d'Astrophysique SpatialeFR64 papers
- Sorbonne UniversitéFR59 papers
- Institut de Recherche en Astrophysique et PlanétologieFR58 papers
- Université Paris CitéFR57 papers
- Université Paris Sciences et LettresFR53 papers
- Ludwig-Maximilians-Universität MünchenDE52 papers
- CEA Paris-SaclayFR51 papers
29 papers · 1 filter
DP-SPRT: Differentially Private Sequential Probability Ratio Tests
Thomas Michel, Debabrota Basu, Emilie Kaufmann
We revisit Wald's celebrated Sequential Probability Ratio Test for sequential tests of two simple hypotheses, under privacy constraints. We propose DP-SPRT, a wrapper that can be c…
Adaptive collaboration for online personalized distributed learning with heterogeneous clients
Constantin Philippenko, Batiste Le Bars, Kevin Scaman +1
We study the problem of online personalized decentralized learning with statistically heterogeneous clients collaborating to accelerate local training. An important challenge i…
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Rémi Bardenet, Subhroshekhar Ghosh, Hugo Simon-Onfroy +1
Determinantal point processes (DPPs) are random configurations of points with tunable negative dependence. Because sampling is tractable, DPPs are natural candidates for subsamplin…
Differentially Private Best-Arm Identification
Achraf Azize, Marc Jourdan, Aymen Al Marjani +1
Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting u…
FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits
Sunrit Chakraborty, Saptarshi Roy, Debabrota Basu
High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genom…
Towards Instance-Optimality in Online PAC Reinforcement Learning
Aymen Al-Marjani, Andrea Tirinzoni, Emilie Kaufmann
Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability , an -optimal policy in finite-h…
Signal reconstruction using determinantal sampling
Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
We study the approximation of a square-integrable function from a finite number of evaluations on a random set of nodes according to a well-chosen distribution. This is particularl…
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption
Shubhada Agrawal, Timothée Mathieu, Debabrota Basu +1
We investigate the regret-minimisation problem in a multi-armed bandit setting with arbitrary corruptions. Similar to the classical setup, the agent receives rewards generated inde…
Concentrated Differential Privacy for Bandits
Achraf Azize, Debabrota Basu
Bandits serve as the theoretical foundation of sequential learning and an algorithmic foundation of modern recommender systems. However, recommender systems often rely on user-sens…
Dealing with Unknown Variances in Best-Arm Identification
Marc Jourdan, Rémy Degenne, Emilie Kaufmann
The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the variances are known. Despite its practical rele…
Risk-aware linear bandits with convex loss
Patrick Saux, Odalric-Ambrym Maillard
In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively stud…
From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits
Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard
The stochastic multi-arm bandit problem has been extensively studied under standard assumptions on the arm's distribution (e.g bounded with known support, exponential family, etc).…
Sub-sampling for Efficient Non-Parametric Bandit Exploration
Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard
In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (name…
Learning from DPPs via Sampling: Beyond HKPV and symmetry
Rémi Bardenet, Subhroshekhar Ghosh
Determinantal point processes (DPPs) have become a significant tool for recommendation systems, feature selection, or summary extraction, harnessing the intrinsic ability of these…
Kernel interpolation with continuous volume sampling
Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
A fundamental task in kernel methods is to pick nodes and weights, so as to approximate a given function from an RKHS by the weighted sum of kernel translates located at the nodes.…
Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
Cindy Trinh, Emilie Kaufmann, Claire Vernade +1
Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are…
Bayesian Optimization using Deep Gaussian Processes
Ali Hebbal, Loic Brevault, Mathieu Balesdent +2
Bayesian Optimization using Gaussian Processes is a popular approach to deal with the optimization of expensive black-box functions. However, because of the a priori on the station…
A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players
Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian +1
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved…
A determinantal point process for column subset selection
Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
Dimensionality reduction is a first step of many machine learning pipelines. Two popular approaches are principal component analysis, which projects onto a small number of well cho…
Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling
Emilie Kaufmann, Wouter Koolen, Aurelien Garivier
Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning…
Decentralized learning with budgeted network load using Gaussian copulas and classifier ensembles
John Klein, Mahmoud Albardan, Benjamin Guedj +1
We examine a network of learners which address the same classification task but must learn from different data sets. The learners cannot share data but instead share their models.…
Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence
Maryam Aziz, Jesse Anderton, Emilie Kaufmann +1
We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir dist…
Bayesian nonparametric Principal Component Analysis
Clément Elvira, Pierre Chainais, Nicolas Dobigeon
Principal component analysis (PCA) is very popular to perform dimension reduction. The selection of the number of significant components is essential but often based on some practi…
Zonotope hit-and-run for efficient sampling from projection DPPs
Guillaume Gautier, Rémi Bardenet, Michal Valko
Determinantal point processes (DPPs) are distributions over sets of items that model diversity using kernels. Their applications in machine learning include summary extraction and…