This thesis is motivated by the perspective of connecting compressed sensing and machine learning, and more particularly by the exploitation of compressed sensing techniques to reduce the cost of learning tasks. After a reminder of compressed sensing and a quick description of data analysis techniques in which similar ideas are exploited, we propose a framework for estimating probability density mixture parameters in which the training data is compressed into a fixed-size representation. We instantiate this framework on an isotropic Gaussian mixture model. This proof of concept suggests the existence of theoretical guarantees for reconstructing signals belonging to models beyond usual sparse models. We therefore study generalizations of sta...
International audienceIn this paper, following the Compressed Sensing paradigm, we study the problem...
Abstract—This paper determines to within a single mea-surement the minimum number of measurements re...
42 pages, 37 figures, 3 appendixesInternational audienceCompressed sensing is a signal processing me...
This thesis is motivated by the perspective of connecting compressed sensing and machine learning, a...
Cette thèse est motivée par la perspective de rapprochement entre traitement du signal et apprentiss...
A novel framework of compressed sensing, namely statistical compressed sensing (SCS), that aims at e...
to appear in Information and Inference, a journal of the IMA (available online since December 2017)I...
A new framework of compressive sensing (CS), namely statistical compres-sive sensing (SCS), that aim...
International audienceWhen performing a learning task on voluminous data, memory and computational t...
Compressed sensing allows to reconstruct a signal from a few linear projections, under the assumptio...
This paper introduces a simple and very general theory of compressive sensing. In this theory, the s...
Compressed Sensing concerns a new class of linear data acquisition protocols that are more efficient...
Compressed sensing takes advantage that most of the natural signals can be sparsely represented via ...
Abstract. Compressed Sensing (CS) seeks to recover an unknown vector with N entries by making far fe...
International audienceIn this work, we consider compressed sensing reconstruction from M measurement...
International audienceIn this paper, following the Compressed Sensing paradigm, we study the problem...
Abstract—This paper determines to within a single mea-surement the minimum number of measurements re...
42 pages, 37 figures, 3 appendixesInternational audienceCompressed sensing is a signal processing me...
This thesis is motivated by the perspective of connecting compressed sensing and machine learning, a...
Cette thèse est motivée par la perspective de rapprochement entre traitement du signal et apprentiss...
A novel framework of compressed sensing, namely statistical compressed sensing (SCS), that aims at e...
to appear in Information and Inference, a journal of the IMA (available online since December 2017)I...
A new framework of compressive sensing (CS), namely statistical compres-sive sensing (SCS), that aim...
International audienceWhen performing a learning task on voluminous data, memory and computational t...
Compressed sensing allows to reconstruct a signal from a few linear projections, under the assumptio...
This paper introduces a simple and very general theory of compressive sensing. In this theory, the s...
Compressed Sensing concerns a new class of linear data acquisition protocols that are more efficient...
Compressed sensing takes advantage that most of the natural signals can be sparsely represented via ...
Abstract. Compressed Sensing (CS) seeks to recover an unknown vector with N entries by making far fe...
International audienceIn this work, we consider compressed sensing reconstruction from M measurement...
International audienceIn this paper, following the Compressed Sensing paradigm, we study the problem...
Abstract—This paper determines to within a single mea-surement the minimum number of measurements re...
42 pages, 37 figures, 3 appendixesInternational audienceCompressed sensing is a signal processing me...