We study classical statistical problems such as as community detection on graphs, Principal Component Analysis (PCA), sparse PCA, Gaussian mixture clustering, linear and generalized linear models, in a Bayesian framework. We compute the best estimation performance (often denoted as ``Bayes Risk'') achievable by any statistical method in the high dimensional regime. This allows to observe surprising phenomena: for many problems, there exists a critical noise level above which it is impossible to estimate better than random guessing.Below this threshold, we compare the performance of existing polynomial-time algorithms to the optimal one and observe a gap in many situations: even if non-trivial estimation is theoretically possible, computatio...
This thesis deals with two models of random walks. The first model belongs to the family of random w...
Machine learning can be de ned as the application of arti cial intelligence that provides systems w...
Many tools exist to solve constrained path-planning problems. They can be classified as follows. In ...
Causal discovery is of utmost importance for agents who must plan, reason anddecide based on observa...
In this thesis, we study problems related to learning and detecting multivariate statistical dissimi...
The first part of this thesis concerns the inference of un-normalized statistical models. We study t...
The subject of this thesis is the study of various models of random walks on random trees, with an e...
One treats the Hausdorff moment problem, the deconvolution on the sphere one and the problem of regr...
Applied mathematics and machine computations have raised a lot of hope since the recent success of s...
Cette thèse s'inscrit dans le cadre de l'analyse statistique en grande dimension. Plus précisé- men...
With the constantly increasing precision of experimental data acquired at the current collider exper...
In this PhD thesis we study general linear model (multivariate linearmodel) in high dimensional sett...
Rare event dedicated techniques are of great interest for the aerospace industry because of the larg...
Rigorous numerics aims at providing certified representations for solutions of various problems, not...
One of the main goals of the ATLAS experiment is the search for the Higgs boson, the last missing in...
This thesis deals with two models of random walks. The first model belongs to the family of random w...
Machine learning can be de ned as the application of arti cial intelligence that provides systems w...
Many tools exist to solve constrained path-planning problems. They can be classified as follows. In ...
Causal discovery is of utmost importance for agents who must plan, reason anddecide based on observa...
In this thesis, we study problems related to learning and detecting multivariate statistical dissimi...
The first part of this thesis concerns the inference of un-normalized statistical models. We study t...
The subject of this thesis is the study of various models of random walks on random trees, with an e...
One treats the Hausdorff moment problem, the deconvolution on the sphere one and the problem of regr...
Applied mathematics and machine computations have raised a lot of hope since the recent success of s...
Cette thèse s'inscrit dans le cadre de l'analyse statistique en grande dimension. Plus précisé- men...
With the constantly increasing precision of experimental data acquired at the current collider exper...
In this PhD thesis we study general linear model (multivariate linearmodel) in high dimensional sett...
Rare event dedicated techniques are of great interest for the aerospace industry because of the larg...
Rigorous numerics aims at providing certified representations for solutions of various problems, not...
One of the main goals of the ATLAS experiment is the search for the Higgs boson, the last missing in...
This thesis deals with two models of random walks. The first model belongs to the family of random w...
Machine learning can be de ned as the application of arti cial intelligence that provides systems w...
Many tools exist to solve constrained path-planning problems. They can be classified as follows. In ...