This thesis presents my main research activities in statistical machine learning aftermy PhD, starting from my post-doc at UC Berkeley to my present research position atInria Grenoble. The first chapter introduces the context and a summary of my scientificcontributions and emphasizes the importance of pluri-disciplinary research. For instance,mathematical optimization has become central in machine learning and the interplay betweensignal processing, statistics, bioinformatics, and computer vision is stronger thanever. With many scientific and industrial fields producing massive amounts of data, theimpact of machine learning is potentially huge and diverse. However, dealing with massivedata raises also many challenges. In this context, the m...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
This thesis presents my main research activities in statistical machine learning aftermy PhD, starti...
Les algorithmes d'apprentissage profond forment un nouvel ensemble de méthodes puissantes pour l'ap...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Les tâches de vision artificielle telles que la reconnaissance d’objets demeurent irrésolues à ce jou...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
This thesis presents my main research activities in statistical machine learning aftermy PhD, starti...
Les algorithmes d'apprentissage profond forment un nouvel ensemble de méthodes puissantes pour l'ap...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
Les tâches de vision artificielle telles que la reconnaissance d’objets demeurent irrésolues à ce jou...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
Neural network models able to approximate and sample high-dimensional probability distributions are ...