**Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?**

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Personne# Paul Thierry Yves Rolland

Official source

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Unités associées

Chargement

Cours enseignés par cette personne

Chargement

Domaines de recherche associés

Chargement

Publications associées

Chargement

Personnes menant des recherches similaires

Chargement

Cours enseignés par cette personne

Aucun résultat

Unités associées (3)

Domaines de recherche associés (5)

Algorithme

thumb|Algorithme de découpe d'un polygone quelconque en triangles (triangulation).
Un algorithme est une suite finie et non ambiguë d'instructions et d’opérations permettant de résoudre une classe de

Neural network

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neur

Loi normale

En théorie des probabilités et en statistique, les lois normales sont parmi les lois de probabilité les plus utilisées pour modéliser des phénomènes naturels issus de plusieurs événements aléatoires.

Publications associées (11)

Chargement

Chargement

Chargement

Personnes menant des recherches similaires (94)

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same environment. However, the real world is most of the time not static, and the environment in which the model will be used can differ from the one in which it is trained. It is hence desirable to design models that are robust to changes of environments. This encapsulates a large family of topics in ML, such as adversarial robustness, meta-learning, domain adaptation and others, depending on the way the environment is perturbed.In this dissertation, we focus on methods for training models whose performance does not drastically degrade when applied to environments differing from the one the model has been trained in. Various types of environmental changes will be treated, differing in their structure or magnitude. Each setup defines a certain kind of robustness to certain environmental changes, and leads to a certain optimization problem to be solved. We consider 3 different setups, and propose algorithms for solving each associated problem using 3 different types of methods, namely, min-max optimization (Chapter 2), regularization (Chapter 3) and variable selection (Chapter 4).Leveraging the framework of distributionally robust optimization, which phrases the problem of robust training as a min-max optimization problem, we first aim to train robust models by directly solving the associated min-max problem. This is done by exploiting recent work on game theory as well as first-order sampling algorithms based on Langevin dynamics. Using this approach, we propose a method for training robust agents in the scope of Reinforcement Learning.We then treat the case of adversarial robustness, i.e., robustness to small arbitrary perturbation of the model's input. It is known that neural networks trained using classical optimization methods are particularly sensitive to this type of perturbations. The adversarial robustness of a model is tightly connected to its smoothness, which is quantified by its so-called Lipschitz constant. This constant measures how much the model's output changes upon any bounded input perturbation. We hence develop a method to estimate an upper bound on the Lipschitz constant of neural networks via polynomial optimization, which can serve as a robustness certificate against adversarial attacks. We then propose to penalize the Lipschitz constant during training by minimizing the 1-path-norm of the neural network, and we develop an algorithm for solving the resulting regularized problem by efficiently computing the proximal operator of the 1-path-norm term, which is non-smooth and non-convex.Finally, we consider a scenario where the environmental changes can be arbitrary large (as opposed to adversarial robustness), but need to preserve a certain causal structure. Recent works have demonstrated interesting connections between robustness and the use of causal variables. Assuming that certain mechanisms remain invariant under some change of the environment, it has been shown that knowing the underlying causal structure of the data at hand allows to train models that are invariant to such changes. Unfortunately, in many cases, the causal structure is unknown. We thus propose a causal discovery algorithm from observational data in the case of non-linear additive model.

Volkan Cevher, Paul Thierry Yves Rolland

This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal discovery methods. To showcase our approach, we also propose a new efficient method for approximating the score’s Jacobian, enabling to recover the causal graph. Empirically, we find that the new algorithm, called SCORE, is competitive with state-of-theart causal discovery methods while being significantly faster.

2022, , ,

While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert’s behavior. It is well known that, in general, various reward functions can lead to the same optimal policy, and hence, IRL is ill-defined. However, [1] showed that, if we observe two or more experts with different discount factors or acting in different environments, the reward function can under certain conditions be identified up to a constant. This work starts by showing an equivalent identifiability statement from multiple experts in tabular MDPs based on a rank condition, which is easily verifiable and is shown to be also necessary. We then extend our result to various different scenarios, i.e., we characterize reward identifiability in the case where the reward function can be represented as a linear combination of given features, making it more interpretable, or when we have access to approximate transition matrices. Even when the reward is not identifiable, we provide conditions characterizing when data on multiple experts in a given environment allows to generalize and train an optimal agent in a new environment. Our theoretical results on reward identifiability and generalizability are validated in various numerical experiments.

2022