Deep learning models are artificial neural networks and they have arisen as the current most competitive method to make data-driven decisions. In classification, these networks have a more complex representation of data and thus they make more complex predictions. However, deep learning's recent successes are also due to the development of some mathematical fields: this thesis is about studying the different interactions of deep learning with one of these mathematical fields called Optimal Transport (OT). To measure the distance between probability distributions, one can rely on the OT theory. It defines a measure through the minimal displacement cost of a distribution to another. Its strength is to use the space geometry with a given groun...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We p...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Les modèles d'apprentissage profond sont des réseaux de neurones artificiels et sont très compétitif...
Despite numerous successes in a wide range of industrial and scientific applications, the learning p...
Neurips 2021 Optimal Transport and Machine Learning WorkshopOptimal transport distances (OT) have be...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
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...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We p...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Deep learning models are artificial neural networks and they have arisen as the current most competi...
Les modèles d'apprentissage profond sont des réseaux de neurones artificiels et sont très compétitif...
Despite numerous successes in a wide range of industrial and scientific applications, the learning p...
Neurips 2021 Optimal Transport and Machine Learning WorkshopOptimal transport distances (OT) have be...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
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...
This thesis proposes theoretical and numerical contributions to use Entropy-regularized Optimal Tran...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Residual connections are ubiquitous in deep learning, since besides residual networks and their vari...
Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We p...