Université Côte d'Azur
CNRS UMR 7351
Parc Valrose, 06108 Nice, Cedex 2, France
+33 (0) 4 89 15 04 96
- Neurosciences and cognition : analysis of
spikes trains and functional connectivity, learning
- Adaptive Statistics : Model selection, Lasso
and multiple testing
- Point processes : Hawkes, Poisson, Aalen
- Concentration inequalities
biostatistician at CHU - Nice
engineer EDF-LJAD on the prediction of sismic
scientist for Talent Consulting
exchange from Verona University
partnership with deligeo
 Phi, Tien Cuong; Muzy, Alexandre; Reynaud-Bouret,
scheduling algorithms with Kalikow decomposition for
simulating potentially infinite neuronal networks,
SN Computer Science, 1(35) (2020).
 Ost, Guilherme; Reynaud-Bouret, Patricia Sparse space-time
models: concentration inequalities and Lasso,
Annales de l'IHP, Probabilités et Statistiques, to appear
 Coeurjolly, Jean-François; Reynaud-Bouret, Patricia A
concentration inequality for inhomogeneous Neymann-Scott
processes, Statistics and Probability Letters, 148,
 Hodara, Pierre; Reynaud-Bouret, Patricia
inequality for chaos based on sampling without
replacement, Statistics and Probability Letters,
146, 65-69 (2019).
 Hunt, Xin Jiang; Reynaud-Bouret, Patricia; Rivoirard,
Vincent; Sansonnet, Laure; Willett, Rebecca A
data-dependent weighted LASSO under Poisson noise, IEEE
Transactions on Information Theory, 65(3), 1589-1613 (2019).
 Picard, Franck; Reynaud-Bouret, Patricia; Roquain,
testing for Poisson process intensities: a new perspective
on scanning statistics, Biometrika, 105(4),
 Lambert, Régis; Tuleau-Malot, Christine; Bessaih, Thomas;
Rivoirard, Vincent; Bouret, Yann; Leresche, Nathalie;
Reynaud-Bouret, Patricia Reconstructing
the functional connectivity of multiple spike trains using
Hawkes models, Journal of Neuroscience Methods,
297, 9-21 (2018)
 Albert, Mélisande ;
Bouret, Yann ; Fromont, Magalie ; Reynaud-Bouret , Patricia Surrogate data methods based on a shuffling of
the trials for synchrony detection: the centering issue, Neural Computation, 28(11), 2352-2392 (2016).
Fromont, Magalie ; Lerasle, Matthieu ; Reynaud-Bouret,
Patricia Family Wise Separation Rates for multiple testing, Annals of Statistics, 44(6), 2533-2563 (2016).
 Lerasle, Matthieu ;
Magalhães, Nelo ; Reynaud-Bouret, Patricia Optimal
kernel selection for density estimation High Dimensional
Probability VII : The Cargese Volume, Prog. Probab. 71,
Birkhaüser, 425-460 (2016).
 Chevallier, Julien ; Cáceres, María José ;
Doumic, Marie ; Reynaud-Bouret, Patricia Microscopic
approach of a time elapsed neural model, Mathematical Models and Methods in Applied
Sciences, 25(14), 2669-2719 (2015).
Albert, Mélisande ; Bouret, Yann ; Fromont, Magalie ;
Reynaud-Bouret, Patricia Bootstrap and permutation tests
of independence for point processes, Annals of Statistics, 43(6), 2537-2564 (2015).
 Tuleau-Malot, Christine ; Rouis, Amel ; Grammont,
Franck ; Reynaud-Bouret, Patricia Multiple tests based on a Gaussian approximation
of the Unitary Events method with delayed coincidence count, Neural Computation, 26(7), 1408-1454 (2014).
 Reynaud-Bouret, Patricia ; Rivoirard,
Vincent ; Grammont , Franck ; Tuleau-Malot, Christine Goodness-of-fit tests and nonparametric
adaptive estimation for spike train analysis, Journal of Mathematical Neuroscience, 4:3 (2014).
 Reynaud-Bouret, Patricia Concentration inequalities, counting
processes and adaptive statistics, ESAIM
Proc. (proceedings of "Journées MAS 2012"), 44, 79-98
Reynaud-Bouret, Patricia ; Rivoirard, Vincent; Tuleau-Malot,
Christine Inference of functional connectivity in
Neurosciences via Hawkes processes, 1st IEEE Global Conference on Signal and
Information Processing, Austin, Texas (2013).
 Hansen, Niels R. ; Reynaud-Bouret, Patricia ; Rivoirard, Vincent Lasso and probabilistic inequalities for
multivariate point processes
21(1), 83-143 (2015).
Magalie ; Laurent, Béatrice ; Reynaud-Bouret, Patricia The two-sample problem for Poisson processes:
adaptive tests with a non-asymptotic wild bootstrap approach
Annals of Statistics, 41(3), 1431-1461 (2013).
Magalie ; Laurent, Béatrice ; Lerasle, Matthieu ; Reynaud-Bouret, Patricia Kernels based tests with
non-asymptotic bootstrap approaches for two-sample problems
JMLR : Workshop and Conference Proceedings, 23, 25th Annual
Conference on Learning Theory, 23.1–23.22 (2012).
 Doumic -Jauffret,
Marie ; Hoffmann, Marc ; Reynaud-Bouret, Patricia ; Rivoirard,
Vincent Nonparametric estimation of the
division rate of a size-structured population, SIAM
Journal on Numerical Analysis, 50, 925-950 (2012).
 Reynaud-Bouret, Patricia ; Rivoirard, Vincent ;
Tuleau-Malot, Christine Adaptive density
estimation: a curse of support?
J. Statist. Plann. Inference, 141, 115-139
 Fromont, Magalie ;
Laurent, Béatrice ; Reynaud-Bouret, Patricia Adaptive test of
homogeneity for a Poisson process Ann. Inst. H. Poincaré Probab. Statist. 47 (1),
Patricia ; Schbath,
Sophie Adaptive estimation
for Hawkes processes; application to genome analysis
Annals of Statististics, 38(5), 2781-2822 (2010).
Patricia ; Rivoirard,
optimal thresholding estimation
of a Poisson intensity on the real line
Electronic Journal of Statistics, 4, 172-238 (2010).
 Houdré, Christian ; Marchal,
Philippe ; Reynaud-Bouret, Patricia
for norms of infinitely divisible vectors with independent
components. Bernoulli, 14(4), 926-948 (2008).
 Reynaud-Bouret, Patricia ; Roy,
asymptotic tail estimates for Hawkes
of the Belgian Mathematical Society-Simon Stevin,
13(5), 883-896 (2007) (old version
Patricia Penalized projection estimators of the
Aalen multiplicative intensity. Bernoulli, 12(4), 633-661 (2006).
and exponential inequalities for some suprema
of counting processes. Statistics and Probability Letters, 76(14),
Houdré, Christian ; Reynaud-Bouret,
inequalities, with constants, for U-statistics of order two. Stochastic
inequalities and applications, Progr.
Probab., 56 Birkhäuser,
Basel, 55-69 (2003).
Patricia Adaptive estimation of the intensity of
inhomogeneous Poisson processes via concentration
Theory Related Fields 126 (1), 103-153 (2003)
[g] Mascart, Cyrille; Muzy, Alexandre; Reynaud-Bouret,
event simulation of point processes: a computational
complexity analysis on sparse graphs, submitted
[f] Albert, Mélisande ; Bouret, Yann ; Fromont, Magalie ;
Reynaud-Bouret, Patricia (preliminary work for ) A Distribution Free Unitary
Events Method based on Delayed Coincidence Count
P. ; Tuleau-Malot, C. ; Rivoirard, V. ; Grammont, F.
(preliminary work for ) Spike trains as (in)homogeneous Poisson processes
or Hawkes processes: non-parametric adaptive estimation and
Tuleau-Malot, C. ; Rouis, A. ; Reynaud-Bouret, P. ; Grammont,
F. (preliminary work for ) Multiple Tests Based on a Gaussian Approximation
of the Unitary Events.
Patricia ; Rivoirard,
(preliminary work for ) Calibration of
thresholding rules for Poisson intensity estimation
Patricia ; Rivoirard,
Vincent (preliminary work for ) Adaptive thresholding estimation of a
Poisson intensity with infinite support
Houdré, Christian ;
(preliminary work for ) Concentration for
Infinitely Divisible Vectors with Independent Components
HDR Manuscript : Adaptive
statistical inference for some point processes (Poisson,
2017/2018: Course1 Course2 Basic Tests :
small review (with typos)
 Lucile Sassatelli (I3S) 21 Octobre
introduction on Reinforcement Learning and Deep RL
This presentation is meant
to provide basics of Reinforcement Learning (RL) and introduce
Deep Reinforcement Learning (DRL), for both synthetic and more
realistic problems. While applications of RL are typically limited
to discrete, low-dimensional constraints, recent advances in Deep
RL (DQN for Atari 2600
, and more
lately AlphaGo Zero
demonstrated human-level or super-human performance in complex,
high-dimensional spaces. However, DRL remains an active research
domain and, as often experienced, is not yet a plug-and-play
optimization tool. In this presentation, we will also peek into
this challenging aspect of DRL for general control problems such
as a robot navigation task, discussing difficulties inherent to RL
and most recent approaches to such problems.
 Luc Lehéricy
(LJAD) 18 Novembre 2020
An introduction to the
mathematical proofs of reinforcement learning
Numerous reinforcement learning algorithms have been introduced
these last few years to efficiently solve an increasing vast array
of problems. Despite their variety, most of them rely on a few
well-trodden ideas, the main difficulty being to adapt these ideas
to a specific situation. The goal of this presentation is to give
the mathematical tools to understand two fundamental and easily
generalizable toy-models of reinforcement learning: the stochastic
bandits and adversarial bandits.
 Oussama Sabri (I3S) 9 Décembre 2020 (10h)
Neural basis of learning
Human beings are born with the fascination gift of learning.
With aid of such, they absorb and assimilate knowledge
throughout thier entire life. Reinforcement Learning (RL) is
one of the computational methods that attempt to simulate such
characteristic in a computational environment capable of
learning. However, RL carries different meanings for different
communities from mathematics, computer science, neuroscience
to psychology, etc. In this talk, I will try to clarify in
general the similarities of RL in different
domains and in which ways they differ with a focus on
the neuro-cognitive part of the brain to understand the
mechanisms behind human/animal learning and decision-making
Giovanni Gatti Pinheiro and Michaël Defoin-Platel (Amadeus) 9
Janvier 2021 (10h)
Airline Revenu Management problem, a general overview on
current state-of-the-art systems and possible extensions
through the Reinforcement Learning framework.
Athanasios Vasileiadis (LJAD) 27 Janvier 2021 (10h)
Stochastic control and reinforcement
learning : How to solve a stochastic control problem using
In this series of talks, we are going to study the interaction
between stochastic control problem and reinforcement learning.
In the first part, we will use reinforcement learning to solve
a stochastic control problem, we will deviate from the
traditional approximate dynamic programming methods and
instead we focus on direct approximation of the feedback
function by deep neural networks DNN and stochastic gradient
descent SGD. Two algorithms will be proposed by a combination
of DNN, sequential dynamic programming DP and MonteCarlo
simulation MC.This approach is commonly referred in the
literature as deep reinforcement learning.
Mathieu Laurière (Princeton) 8 Avril 2021 (15h)
On Mean-Field Markov Decision Processes
and Mean-Field Q-Learning
Mean-field game theory borrows ideas from statistical physics
to provide a tractable approximation of very large multi-agent
systems. Applications are ubiquitous in today's highly
interconnected world, from crowd motion to macroeconomics and
distributed robotics. Real-world problems often lead to models
which are not fully known to the agents, hence a recent surge
of interests for the question of computing solutions with
model-free methods. In this talk, we will mainly focus on a
framework for reinforcement learning with mean-field
interactions. In this talk, we focus on the case where the
agents are cooperative and look for a social optimum. We
formulate a notion of mean-field Markov Decision Process
(MDP), and we prove a dynamic programming principle for the
state value function and state-action value function. Based on
the latter function, we propose a mean-field Q-learning
method. We prove its convergence under suitable conditions and
provide numerical examples. Joint work with René Carmona and