Search Results for author:
Found 35 papers, 3 papers with code
Beyond Average Return in Markov Decision Processes
What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes? In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain classes of statistics.
About the Cost of Central Privacy in Density Estimation
We recover the result of Barber \& Duchi (2014) stating that histogram estimators are optimal against Lipschitz distributions for the L2 risk, and under regular differential privacy, and we extend it to other norms and notions of privacy.
Private Statistical Estimation of Many Quantiles
The first one consists in privately estimating the empirical quantiles of the samples and using this result as an estimator of the quantiles of the distribution.
Regret Analysis of the Stochastic Direct Search Method for Blind Resource Allocation
This is a realistic model for budget allocation across subdivisions of marketing campaigns, when the objective is to maximize the number of conversions.
On the Statistical Complexity of Estimation and Testing under Privacy Constraints
In certain scenarios, we show that maintaining privacy results in a noticeable reduction in performance only when the level of privacy protection is very high.
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits
All these new upper and lower bounds generalize existing bounds based, e. g., on gaps between distributions.
Private Quantiles Estimation in the Presence of Atoms
We consider the differentially private estimation of multiple quantiles (MQ) of a distribution from a dataset, a key building block in modern data analysis.
On the complexity of All $\varepsilon$-Best Arms Identification
Our method is based on a complete characterization of the alternative bandit instances that the optimal sampling strategy needs to rule out, thus making our bound tighter than the one provided by \cite{Mason2020}.
Sequential Algorithms for Testing Closeness of Distributions
For a general alphabet size $n$, we give a sequential algorithm that uses no more samples than its batch counterpart, and possibly fewer if the actual distance between $\mathcal{D}_1$ and $\mathcal{D}_2$ is larger than $\epsilon$.
A/B/n Testing with Control in the Presence of Subpopulations
At every time step, a subpopulation is sampled and an arm is chosen: the resulting observation is an independent draw from the arm conditioned on the subpopulation.
Fast Rate Learning in Stochastic First Price Bidding
First-price auctions have largely replaced traditional bidding approaches based on Vickrey auctions in programmatic advertising.
Navigating to the Best Policy in Markov Decision Processes
We investigate the classical active pure exploration problem in Markov Decision Processes, where the agent sequentially selects actions and, from the resulting system trajectory, aims at identifying the best policy as fast as possible.
A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits
We propose a new strategy for best-arm identification with fixed confidence of Gaussian variables with bounded means and unit variance.
Efficient Algorithms for Stochastic Repeated Second-price Auctions
We further provide the first parametric lower bound for this problem that applies to generic UCB-like strategies.
Self-Concordant Analysis of Generalized Linear Bandits with Forgetting
Contextual sequential decision problems with categorical or numerical observations are ubiquitous and Generalized Linear Bandits (GLB) offer a solid theoretical framework to address them.
Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs.
Best Arm Identification in Spectral Bandits
We study best-arm identification with fixed confidence in bandit models with graph smoothness constraint.
Algorithms for Non-Stationary Generalized Linear Bandits
The statistical framework of Generalized Linear Models (GLM) can be applied to sequential problems involving categorical or ordinal rewards associated, for instance, with clicks, likes or ratings.
X-Armed Bandits: Optimizing Quantiles, CVaR and Other Risks
We finally present numerical experiments that show a dramatic impact of tight bounds for the optimization of quantiles and CVaR.
A Review on Quantile Regression for Stochastic Computer Experiments
We report on an empirical study of the main strategies for quantile regression in the context of stochastic computer experiments.
Optimization of a SSP's Header Bidding Strategy using Thompson Sampling
The SSP acts as an intermediary between an advertiser wanting to buy ad spaces and a web publisher wanting to sell its ad spaces, and needs to define a bidding strategy to be able to deliver to the advertisers as many ads as possible while spending as little as possible.
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints
We were able to obtain this non-parametric bi-optimality result while working hard to streamline the proofs (of previously known regret bounds and thus of the new analyses carried out); a second merit of the present contribution is therefore to provide a review of proofs of classical regret bounds for index-based strategies for $K$-armed stochastic bandits.
Profitable Bandits
We adapt and study three well-known strategies in this purpose, that were proved to be most efficient in other settings: kl-UCB, Bayes-UCB and Thompson Sampling.
Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing.
Max K-armed bandit: On the ExtremeHunter algorithm and beyond
This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values.
A minimax and asymptotically optimal algorithm for stochastic bandits
We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions.
Learning the distribution with largest mean: two bandit frameworks
Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization.
On Explore-Then-Commit Strategies
We study the problem of minimising regret in two-armed bandit problems with Gaussian rewards.
Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
We revisit lower bounds on the regret in the case of multi-armed bandit problems.
Optimal Best Arm Identification with Fixed Confidence
We give a complete characterization of the complexity of best-arm identification in one-parameter bandit problems.
Maximin Action Identification: A New Bandit Framework for Games
We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search.
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
The stochastic multi-armed bandit model is a simple abstraction that has proven useful in many different contexts in statistics and machine learning.
On the Complexity of A/B Testing
A/B testing refers to the task of determining the best option among two alternatives that yield random outcomes.
The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond
This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems.
Parametric Bandits: The Generalized Linear Case
We consider structured multi-armed bandit tasks in which the agent is guided by prior structural knowledge that can be exploited to efficiently select the optimal arm(s) in situations where the number of arms is large, or even infinite.
