List of Publications

We study the problem of sequential learning of the Pareto front in multi-objective multi-armed bandits. An agent is faced with K possible arms to pull. At each turn she picks one, and receives a vector-valued reward. When she thinks she has enough information to identify the Pareto front of the different arm means, she stops the game and gives an answer. We are interested in designing algorithms such that the answer given is correct with probability at least 1-δ. Our main contribution is an efficient implementation of an algorithm achieving the optimal sample complexity when the risk δ is small. With K arms in d dimensions p of which are in the Pareto set, the algorithm runs in time O(Kp^d) per round.

Abstract 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. We summarize the characterization of these classes for policy evaluation, and give a new answer for the planning problem. Interestingly, we prove that only generalized means can be optimized exactly, even in the more general framework of Distributional Reinforcement Learning (DistRL). DistRL permits, however, to evaluate other functionals approximately. We provide error bounds on the resulting estimators, and discuss the potential of this approach as well as its limitations. These results contribute to advancing the theory of Markov Decision Processes by examining overall characteristics of the return, and particularly risk-conscious strategies.

We study non-parametric density estimation for densities in Lipschitz and Sobolev spaces, and under global privacy. In particular, we investigate regimes where the privacy budget is not supposed to be constant. We consider the classical definition of global differential privacy, but also the more recent notion of global concentrated differential privacy. 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. Then, we investigate higher degrees of smoothness, drawing two conclusions: First, and contrary to what happens with constant privacy budget (Wasserman & Zhou, 2010), there are regimes where imposing privacy degrades the regular minimax risk of estimation on Sobolev densities. Second, so-called projection estimators are near-optimal against the same classes of densities in this new setup with pure differential privacy, but contrary to the constant privacy budget case, it comes at the cost of relaxation. With zero concentrated differential privacy, there is no need for relaxation, and we prove that the estimation is optimal.

In the problem of quantum channel certification, we have black box access to a quantum process and would like to decide if this process matches some predefined specification or is ε-far from this specification. The objective is to achieve this task while minimizing the number of times the black box is used. Here, we focus on optimal incoherent strategies for two relevant extreme cases of channel certification. The first one is when the predefined specification is a unitary channel, e.g., a gate in a quantum circuit. In this case, we show that testing whether the black box is described by a fixed unitary operator in dimension d or ε-far from it in the trace norm requires Θ(d/ε^2) uses of the black box. The second setting we consider is when the predefined specification is a completely depolarizing channel with input dimension din and output dimension dout. In this case, we prove that, in the non-adaptive setting, Θ(d_in^2 d_out^1.5 / ε^2) uses of the channel are necessary and sufficient to verify whether it is equal to the depolarizing channel or ε-far from it in the diamond norm. Finally, we prove a lower bound of Ω(d_in^2d_out/ε^2) for this problem in the adaptive setting. Note that the special case d_in=1 corresponds to the well-studied quantum state certification problem.

We address the differentially private estimation of multiple quantiles (MQ) of a dataset, a key building block in modern data analysis. We apply the recent non-smoothed Inverse Sensitivity (IS) mechanism to this specific problem and establish that the resulting method is closely related to the current state-of-the-art, the JointExp algorithm, sharing in particular the same computational complexity and a similar efficiency. However, we demonstrate both theoretically and empirically that (non-smoothed) JointExp suffers from an important lack of performance in the case of peaked distributions, with a potentially catastrophic impact in the presence of atoms. While its smoothed version would allow to leverage the performance guarantees of IS, it remains an open challenge to implement. As a proxy to fix the problem we propose a simple and numerically efficient method called Heuristically Smoothed JointExp (HSJointExp), which is endowed with performance guarantees for a broad class of distributions and achieves results that are orders of magnitude better on problematic datasets.

We consider the problem introduced by [MJTN20] of identifying all the ε-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards. In the fixed confidence setting, we give a lower bound on the number of samples required by any algorithm that returns the set of ε-good arms with a failure probability less than some risk level δ. This bound writes as T * ε (µ) log(1/δ), where T * ε (µ) is a characteristic time that depends on the vector of mean rewards µ and the accuracy parameter ε. We also provide an efficient numerical method to solve the convex max-min program that defines the characteristic time. 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 [MJTN20]. Using this method, we propose a Track-and-Stop algorithm that identifies the set of ε-good arms w.h.p and enjoys asymptotic optimality (when δ goes to zero) in terms of the expected sample complexity. Finally, using numerical simulations, we demonstrate our algorithm's advantage over state-of-the-art methods, even for moderate values of the risk parameter.

We propose a new strategy for best-arm identification with fixed confidence of Gaussian variables with bounded means and unit variance. This strategy called Exploration-Biased Sampling is not only asymptotically optimal: we also prove non-asymptotic bounds occurring with high probability. To the best of our knowledge, this is the first strategy with such guarantees. But the main advantage over other algorithms like Track-and-Stop is an improved behavior regarding exploration: Exploration-Biased Sampling is slightly biased in favor of exploration in a subtle but natural way that makes it more stable and interpretable. These improvements are allowed by a new analysis of the sample complexity optimization problem, which yields a faster numerical resolution scheme and several quantitative regularity results that we believe of high independent interest.

Developing efficient sequential bidding strategies for repeated auctions is an important practical challenge in various marketing tasks. In this setting, the bidding agent obtains information, on both the value of the item at sale and the behavior of the other bidders, only when she wins the auction. Standard bandit theory does not apply to this problem due to the presence of action-dependent censoring. In this work, we consider second-price auctions and propose novel, efficient UCB-like algorithms for this task. These algorithms are analyzed in the stochastic setting, assuming regularity of the distribution of the opponents' bids. We provide regret upper bounds that quantify the improvement over the baseline algorithm proposed in the literature. The improvement is particularly significant in cases when the value of the auctioned item is low, yielding a spectacular reduction in the order of the worst-case regret. We further provide the first parametric lower bound for this problem that applies to generic UCB-like strategies. As an alternative, we propose more explainable strategies which are reminiscent of the Explore Then Commit bandit algorithm. We provide a critical analysis of this class of strategies, showing both important advantages and limitations. In particular, we provide a minimax lower bound and propose a nearly minimax-optimal instance of this class.

We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsening method having strong theoretical guarantees with mutual information maximization suffices to produce high quality embeddings. We evaluate them on classification tasks with common benchmarks of the literature. We show that our algorithm is competitive with state of the art among unsupervised graph representation learning methods.

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. In the example of binary rewards, logistic regression is well-known to be preferable to the use of standard linear modeling. Previous works have shown how to deal with GLMs in contextual online learning with bandit feedback when the environment is assumed to be stationary. In this paper, we relax this latter assumption and propose two upper confidence bound based algorithms that make use of either a sliding window or a discounted maximum-likelihood estimator. We provide theoretical guarantees on the behavior of these algorithms for general context sequences and in the presence of abrupt changes. These results take the form of high probability upper bounds for the dynamic regret that are of order d^2/3 G^1/3 T^2/3 , where d, T and G are respectively the dimension of the unknown parameter, the number of rounds and the number of breakpoints up to time T. The empirical performance of the algorithms is illustrated in simulated environments.

We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing. In each case, we provide a lower bound valid... more

We propose and analyze StoROO, an algorithm for risk optimization on stochastic black-box functions derived from StoOO. Motivated by risk-averse decision making fields like agriculture, medicine,... more

(poster) Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search... more

We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions. We prove that it is simultaneously asymptotically optimal (in the... more

We study the problem of minimising regret in two-armed bandit problems with Gaussian rewards. Our objective is to use this simple setting to illustrate that strategies based on an exploration... more

We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample... more

For several web tasks such as ad placement or e-commerce, recommender systems must recommend multiple items to their users---such problems can be modeled as bandits with multiple plays. State-of-... more

Après obtention de leur DUT, de nombreux étudiants des IUT STID souhaitent poursuivre leurs études pour obtenir un Master qui leur donne la possibilité de travailler comme ingénieur-expert ou chef... more

Stochastic bandit problems have been analyzed from two different perspectives: a frequentist view, where the parameter is a deterministic unknown quantity, and a Bayesian approach, where the... more

Many problems, such as cognitive radio, parameter control of a scanning tunnelling microscope or internet advertisement, can be modelled as non-stationary bandit problems where the distributions... more

We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out... more

This paper is devoted to extend the regenerative block-bootstrap (RBB) proposed for regenerative Markov chains to Hidden Markov Models {(Xn, Yn)}. In the HMM setup, regeneration times of the... more

Particle filtering has been successfully used to approximate the fixed-lag or fixed-interval smoothing distributions in digital communication and to perform approximate maximum likelihood... more