Search Results for author:
Found 59 papers, 7 papers with code
The Value of Reward Lookahead in Reinforcement Learning
In particular, we measure the ratio between the value of standard RL agents and that of agents with partial future-reward lookahead.
Mode Estimation with Partial Feedback
The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments.
Local and adaptive mirror descents in extensive-form games
We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback.
Trading-off price for data quality to achieve fair online allocation
We consider the problem of online allocation subject to a long-term fairness penalty.
DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
The Shapley value has recently been proposed as a principled tool to achieve this goal due to formal axiomatic justification.
Constant or logarithmic regret in asynchronous multiplayer bandits
This motivates the harder, asynchronous multiplayer bandits problem, which was first tackled with an explore-then-commit (ETC) algorithm (see Dakdouk, 2022), with a regret upper-bound in $\mathcal{O}(T^{\frac{2}{3}})$.
Adapting to game trees in zero-sum imperfect information games
Imperfect information games (IIG) are games in which each player only partially observes the current game state.
A survey on multi-player bandits
Due mostly to its application to cognitive radio networks, multiplayer bandits gained a lot of interest in the last decade.
Stochastic Mirror Descent for Large-Scale Sparse Recovery
In this paper we discuss an application of Stochastic Approximation to statistical estimation of high-dimensional sparse parameters.
On Preemption and Learning in Stochastic Scheduling
We study single-machine scheduling of jobs, each belonging to a job type that determines its duration distribution.
Active Labeling: Streaming Stochastic Gradients
The workhorse of machine learning is stochastic gradient descent.
An algorithmic solution to the Blotto game using multi-marginal couplings
In the case of asymmetric values where optimal solutions need not exist but Nash equilibria do, our algorithm samples from an $\varepsilon$-Nash equilibrium with similar complexity but where implicit constants depend on various parameters of the game such as battlefield values.
Privacy Amplification via Shuffling for Linear Contextual Bandits
Contextual bandit algorithms are widely used in domains where it is desirable to provide a personalized service by leveraging contextual information, that may contain sensitive information that needs to be protected.
Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge
We consider the problem of online linear regression in the stochastic setting.
Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits
In the fixed budget thresholding bandit problem, an algorithm sequentially allocates a budgeted number of samples to different distributions.
Pure Exploration and Regret Minimization in Matching Bandits
Finding an optimal matching in a weighted graph is a standard combinatorial problem.
Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm
Motivated by sequential budgeted allocation problems, we investigate online matching problems where connections between vertices are not i. i. d., but they have fixed degree distributions -- the so-called configuration model.
Unsupervised Neural Hidden Markov Models with a Continuous latent state space
We introduce a new procedure to neuralize unsupervised Hidden Markov Models in the continuous case.
Offline Inverse Reinforcement Learning
Current solutions either solve a behaviour cloning problem (which does not leverage the exploratory data) or a reinforced imitation learning problem (using a fixed cost function that discriminates available exploratory trajectories from expert ones).
Decentralized Learning in Online Queuing Systems
In the centralized case, the number of accumulated packets remains bounded (i. e., the system is \textit{stable}) as long as the ratio between service rates and arrival rates is larger than $1$.
A Generalised Inverse Reinforcement Learning Framework
The gloabal objective of inverse Reinforcement Learning (IRL) is to estimate the unknown cost function of some MDP base on observed trajectories generated by (approximate) optimal policies.
Encrypted Linear Contextual Bandit
A critical aspect of bandit methods is that they require to observe the contexts --i. e., individual or group-level data-- and rewards in order to solve the sequential problem.
Making the most of your day: online learning for optimal allocation of time
If she accepts the proposal, she is busy for the duration of the task and obtains a reward that depends on the task duration.
Be Greedy in Multi-Armed Bandits
On the other hand, this heuristic performs reasonably well in practice and it even has sublinear, and even near-optimal, regret bounds in some very specific linear contextual and Bayesian bandit models.
Quickest change detection for multi-task problems under unknown parameters
We consider the quickest change detection problem where both the parameters of pre- and post- change distributions are unknown, which prevent the use of classical simple hypothesis testing.
Lifelong Learning in Multi-Armed Bandits
Continuously learning and leveraging the knowledge accumulated from prior tasks in order to improve future performance is a long standing machine learning problem.
Robustness of Community Detection to Random Geometric Perturbations
We consider the stochastic block model where connection between vertices is perturbed by some latent (and unobserved) random geometric graph.
Local Differential Privacy for Regret Minimization in Reinforcement Learning
Motivated by this, we study privacy in the context of finite-horizon Markov Decision Processes (MDPs) by requiring information to be obfuscated on the user side.
Social Learning in Non-Stationary Environments
In the simple uni-dimensional and static setting, beliefs about the quality are known to converge to its true value.
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
In CMAB, the question of the existence of an efficient policy with an optimal asymptotic regret (up to a factor poly-logarithmic with the action size) is still open for many families of distributions, including mutually independent outcomes, and more generally the multivariate sub-Gaussian family.
Categorized Bandits
We introduce a new stochastic multi-armed bandit setting where arms are grouped inside ``ordered'' categories.
Selfish Robustness and Equilibria in Multi-Player Bandits
We provide the first algorithm robust to selfish players (a. k. a.
Trajectory representation learning for Multi-Task NMRDPs planning
Expanding Non Markovian Reward Decision Processes (NMRDP) into Markov Decision Processes (MDP) enables the use of state of the art Reinforcement Learning (RL) techniques to identify optimal policies.
Markov Decision Process for MOOC users behavioral inference
Studies on massive open online courses (MOOCs) users discuss the existence of typical profiles and their impact on the learning process of the students.
Online A-Optimal Design and Active Linear Regression
By trying to minimize the $\ell^2$-loss $\mathbb{E} [\lVert\hat{\beta}-\beta^{\star}\rVert^2]$ the decision maker is actually minimizing the trace of the covariance matrix of the problem, which corresponds then to online A-optimal design.
ROI Maximization in Stochastic Online Decision-Making
We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making.
Utility/Privacy Trade-off through the lens of Optimal Transport
Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility.
An adaptive stochastic optimization algorithm for resource allocation
This can be recast as a specific stochastic optimization problem where the objective is to maximize the cumulative reward, or equivalently to minimize the regret.
Exploiting Structure of Uncertainty for Efficient Matroid Semi-Bandits
We improve the efficiency of algorithms for stochastic \emph{combinatorial semi-bandits}.
A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players
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 players receive zero reward.
Regularized Contextual Bandits
We consider the stochastic contextual bandit problem with additional regularization.
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 the best alternative ("best arm identification") or on minimizing the cost (the "regret").
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at the same stage.
Bandits with Side Observations: Bounded vs. Logarithmic Regret
We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\epsilon$, an extra observation is gathered by the agent for free.
Dynamic Pricing with Finitely Many Unknown Valuations
When $K=2$ in the distribution-dependent case, the hardness of our setting reduces to that of a stochastic $2$-armed bandit: we prove that an upper bound of order $(\log T)/\Delta$ (up to $\log\log$ factors) on the regret can be achieved with no information on the demand curve.
Finding the bandit in a graph: Sequential search-and-stop
We consider the problem where an agent wants to find a hidden object that is randomly located in some vertex of a directed acyclic graph (DAG) according to a fixed but possibly unknown distribution.
Stochastic Bandit Models for Delayed Conversions
We assume that the probability of conversion associated with each action is unknown while the distribution of the conversion delay is known, distinguishing between the (idealized) case where the conversion events may be observed whatever their delay and the more realistic setting in which late conversions are censored.
Sparse Stochastic Bandits
In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward.
A comparative study of counterfactual estimators
We provide a comparative study of several widely used off-policy estimators (Empirical Average, Basic Importance Sampling and Normalized Importance Sampling), detailing the different regimes where they are individually suboptimal.
Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe
We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback.
Combinatorial semi-bandit with known covariance
We introduce a way to quantify the dependency structure of the problem and design an algorithm that adapts to it.
Approachability of convex sets in generalized quitting games
The third is necessary: if it is not satisfied, the opponent can weakly exclude the target set.
Highly-Smooth Zero-th Order Online Optimization Vianney Perchet
The minimization of convex functions which are only available through partial and noisy information is a key methodological problem in many disciplines.
Gains and Losses are Fundamentally Different in Regret Minimization: The Sparse Case
We demonstrate that, in the classical non-stochastic regret minimization problem with $d$ decisions, gains and losses to be respectively maximized or minimized are fundamentally different.
Online learning in repeated auctions
To our knowledge, this is the first complete set of strategies for bidders participating in auctions of this type.
Approachability in unknown games: Online learning meets multi-objective optimization
We show that it is impossible, in general, to approach the best target set in hindsight and propose achievable though ambitious alternative goals.
Gaussian Process Optimization with Mutual Information
In this paper, we analyze a generic algorithm scheme for sequential global optimization using Gaussian processes.
A Primal Condition for Approachability with Partial Monitoring
In this paper we provide primal conditions on a convex set to be approachable with partial monitoring.
The multi-armed bandit problem with covariates
We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate.
