This thesis is divided into two parts. In the first part, we show how problems of statistical inference and combinatorial optimization may be approached within a unified framework that employs tools from fields as diverse as machine learning, statistical physics and information theory, allowing us to i) design algorithms to solve the problems, ii) analyze the performance of these algorithms both empirically and analytically, and iii) to compare the results obtained with the optimal achievable ones. In the second part, we use this framework to study two specific problems, one of inference (compressed sensing) and the other of optimization (information hiding). In both cases, we review current approaches, identify their flaws, and propose new...
Resumo: Esta tese de doutorado possui como tema geral o desenvolvimento de algoritmos de Aprendizado...
With the advent of massive datasets, statistical learning and information processing techniques are ...
The central problem of Compressed Sensing is to recover a sparse signal from fewer measurements than...
This thesis is divided into two parts. In the first part, we show how problems of statistical infere...
Nowadays, typical methodologies employed in statistical physics are successfully applied to a huge s...
Neste trabalho, Compressed Sensing é introduzido do ponto de vista da Física Estatística. Após uma i...
Compressed sensing is a new paradigm capable of sampling and compressing signals in one step. Its or...
In the last decades the tl1eory of spin glasses has been developed within the framework of statisti...
Abstract. The combinatorial problem of satisfying a given set of constraints that depend on N discre...
Classically, the performance of estimators in statistical learning problems is measured in terms of ...
We study classical statistical problems such as community detection on graphs, Principal Component A...
The topic of this Ph.D. thesis lies on the borderline between signal processing, statistics and comp...
We study classical statistical problems such as as community detection on graphs, Principal Componen...
42 pages, 37 figures, 3 appendixesInternational audienceCompressed sensing is a signal processing me...
Datasets come in a variety of forms and from a broad range of different applications. Typically, the...
Resumo: Esta tese de doutorado possui como tema geral o desenvolvimento de algoritmos de Aprendizado...
With the advent of massive datasets, statistical learning and information processing techniques are ...
The central problem of Compressed Sensing is to recover a sparse signal from fewer measurements than...
This thesis is divided into two parts. In the first part, we show how problems of statistical infere...
Nowadays, typical methodologies employed in statistical physics are successfully applied to a huge s...
Neste trabalho, Compressed Sensing é introduzido do ponto de vista da Física Estatística. Após uma i...
Compressed sensing is a new paradigm capable of sampling and compressing signals in one step. Its or...
In the last decades the tl1eory of spin glasses has been developed within the framework of statisti...
Abstract. The combinatorial problem of satisfying a given set of constraints that depend on N discre...
Classically, the performance of estimators in statistical learning problems is measured in terms of ...
We study classical statistical problems such as community detection on graphs, Principal Component A...
The topic of this Ph.D. thesis lies on the borderline between signal processing, statistics and comp...
We study classical statistical problems such as as community detection on graphs, Principal Componen...
42 pages, 37 figures, 3 appendixesInternational audienceCompressed sensing is a signal processing me...
Datasets come in a variety of forms and from a broad range of different applications. Typically, the...
Resumo: Esta tese de doutorado possui como tema geral o desenvolvimento de algoritmos de Aprendizado...
With the advent of massive datasets, statistical learning and information processing techniques are ...
The central problem of Compressed Sensing is to recover a sparse signal from fewer measurements than...