I am now a Full-time researcher (CR2) at INRIA Saclay, in the TAO team. I was previously (February 2013 – May 2014) a Postdoctorant at the Technion, then a Senior Researcher at the Technion (June 2014-December 2014) working with Shie Mannor, on the European SUPREL project. Before that, (October 2011 – January 2013) I was doing my first Postdoctorat at University of Leoben, with Peter Auer, within the 4-year European project COMPLACS. I did my PhD in Computer Science and Mathematics at Université of Lille 1. My adviser was Remi Munos (SequeL, INRIA, Lille) and my co-adviser was Philippe Berthet (LSP, IMT, Toulouse).
There are surely much more interesting pages than this blog on the web.
Try for instance [random].
I am interested in providing a theoretical framework for Sequential decision making and Reinforcement learning. For this reason, I mostly play with Bandit theory but not only. This needs understanding properties of empirical processes for small number of samples that can or can not be learned and at which speed. In particular, I am interested in transferring/developping tools from mathematical Statistics to the field of Machine Learning and especially Sequential Learning:
- Sequential Learning theory:
This is a very motivating field of research that adresses the following kind of problems (amongst others): Let consider you have on one hand several statistical processes indexed by time, and on the other hand a property P. Then one typical goal is to detect which one satisfies the property P as soon as possible, i.e. optimally and non-asymptotically. Thus, this field of research is deeply related to:
- Empiricial processes theory.
- Non-asymptotic statistics.
- Information and Coding theory.
- Optimal Stopping theory.
This has many applications also, for instance in order to build adaptive algorithms, and especially in bandit theory, markov decision problems, reinforcement learning, optimization, game theory…
- Statistical theory:
Of course since we need to understand the objects we consider, statistical theory is fundamental. For instance, there are many concentration/large deviation results that are still not understood optimally, like for instance concentration involving the empirical distribution (and not only empirical mean), or concentration of high order moments. There are many others important and difficult questions involving model selection, covershift, sparsity, optimal sensing, empirical penalization, active covering… that are still not solved, especially when we ask for adaptivity.
We have little opportunity, in the academic world, to express one’s feelings, philosophy of life, or enthousiasm about knowledge. We communicate only via research articles and are reduced to disambodied metrics that convey only a partial aspect of what we are. I believe this is sad and counter-productive. As every creative person, we, researchers, have a rich and complex personality that takes time to understand and appreciate.
Let me just give you a glimpse about me, the guy behind the articles, through the following hopefully not-too-arrogant quotes:
“You should act in life in such a way that every person you meet
wants to remember you and include you in the mere definition of its own existence.“
This may be about true love, and true good. Note that making somebody part of your own definition goes far beyond acknowledging somebody, it gives her/him a bit of eternity, an existence beyond its body, it makes him/her a kind of divinity. Thus you should also be infinitely grateful to the persons whom you modified the existence in this way.
“Gaze at stars.”
Because this is the philosophy of mens in south pacific.
Because it makes you realize how tiny you are, and how lucky and unique you are, to have the opportunity to see how wonderful is the universe, to exist and have appeared precisely here and at this time.
Because it gives you a destiny, a responsability as a human being, to act wisely in this tiny life and focus on what really matters.
Because you can never feel lonely under the stars.
Because it gives you hope that you can achieve a high-destiny, and strength in difficult situations.
“Et pourquoi pas ? (And why not?)”.
This is what my great-father, Rene Jouannetaud, used to say. This is today one of my moto. He decided one day to start planting trees. And he planted no less than 30,000 trees in his life. He was not only extraordinary wise, but curious about everything, and deeply connected to the Earth, and Nature. He crafted my first dowser stick, and showed me how to use it. There is nothing like the deep connection you experience when you feel the stick turning in your hand on its own, and testing several times untill you realize you have found the underground river that passes through the village. I feel more than lucky to have known him. I naturally crafted his last stick when he returned to the earth.
” … “
Because I do not consider I am so important as to give you advices. You are smart and strong enough to find your own way, to have your own philosophy your own belief and answers about the world, without needing anybody to tell you what to think, ever. It would be moreover offensive to the divinity inside you.
Illustration of Research
“La première image illustre la quête de la vérité, la bataille, la fougue intellectuelle habitant le chercheur, pour aller vers son but, symbolisé par la troisième image. Celle-ci illustre l’apaisement intellectuel, le bonheur ressenti lors de la découverte d’un théorème, la contemplation du beau et du vrai, l’objet de la quête enfin. En ce sens le chercheur est un chevalier. La deuxième image relie ces deux mondes, par l’intermédiaire de ce clown hirsute ouvrant les bras. C’est ainsi que l’artiste expose tout son art. Ce clown est l’incarnation de la démarche scientifique, décalée, osant les idées les plus folles, et nécessitant l’émotion la plus productive pour accomplir sa tâche: le rire. Ce clown sans le sou traduit également l’humilité du chercheur, et le détachement des choses matérielles. Ainsi va le chercheur, chevalier, clown et artiste à la fois.”