This thesis focuses on statistical inference in graphs (or matrices) in high dimensionand studies the graph alignment problem which aims to recover a hidden underlyingmatching between the nodes of two correlated random graphs.Similarly to many other inference problems in planted models, we are interested in understandingthe fundamental information-theoretical limits as well as the computational hardnessof graph alignment.First, we study the Gaussian setting, when the graphs are complete and the signal lieson correlated Gaussian edges weights. We prove that the exact recovery task exhibits asharp information-theoretic threshold, characterize it, and study a simple and natural spectralmethod for recovery, EIG1, which consists in aligning the ...
We propose two novel approaches for recommender systems and networks. In the first part, we first gi...
This thesis focuses on two topics of graph algorithms. The first topic is network inference. How eff...
We study the consistency of graph matching for estimating a latent alignment function be-tween the v...
This thesis focuses on statistical inference in graphs (or matrices) in high dimensionand studies th...
International audienceRandom graph alignment refers to recovering the underlying vertex corresponden...
33 pages. Typos corrected, some new figures, some remarks and explanations detailed, minor changes i...
Motivated by alignment of correlated sparse random graphs, we introduce a hypothesis testing problem...
The problem of aligning Erdos-Renyi random graphs is a noisy, average-case version of the graph isom...
27 pages, all comments welcomeIn this paper we address the problem of testing whether two observed t...
The problem of aligning Erd\"os-R\'enyi random graphs is a noisy, average-case version of the graph ...
The graph matching problem is, given two graphs, to find the bijection between the vertex sets that ...
This manuscript deals with inference problems on large, usually sparse, random graphs. We first focu...
We study the fundamental limits for reconstruction in weighted graph (or matrix) database alignment....
The thesis considers the estimation of sparse precision matrices in the highdimensional setting. Fir...
On s'intéresse dans ce manuscrit à des problèmes d'inférence dans des graphes aléatoires de grande t...
We propose two novel approaches for recommender systems and networks. In the first part, we first gi...
This thesis focuses on two topics of graph algorithms. The first topic is network inference. How eff...
We study the consistency of graph matching for estimating a latent alignment function be-tween the v...
This thesis focuses on statistical inference in graphs (or matrices) in high dimensionand studies th...
International audienceRandom graph alignment refers to recovering the underlying vertex corresponden...
33 pages. Typos corrected, some new figures, some remarks and explanations detailed, minor changes i...
Motivated by alignment of correlated sparse random graphs, we introduce a hypothesis testing problem...
The problem of aligning Erdos-Renyi random graphs is a noisy, average-case version of the graph isom...
27 pages, all comments welcomeIn this paper we address the problem of testing whether two observed t...
The problem of aligning Erd\"os-R\'enyi random graphs is a noisy, average-case version of the graph ...
The graph matching problem is, given two graphs, to find the bijection between the vertex sets that ...
This manuscript deals with inference problems on large, usually sparse, random graphs. We first focu...
We study the fundamental limits for reconstruction in weighted graph (or matrix) database alignment....
The thesis considers the estimation of sparse precision matrices in the highdimensional setting. Fir...
On s'intéresse dans ce manuscrit à des problèmes d'inférence dans des graphes aléatoires de grande t...
We propose two novel approaches for recommender systems and networks. In the first part, we first gi...
This thesis focuses on two topics of graph algorithms. The first topic is network inference. How eff...
We study the consistency of graph matching for estimating a latent alignment function be-tween the v...