Kernel methods are regarded as a cornerstone of machine learning.They allow to model real-valued functions in expressive functional spaces, over which regularized empirical risk minimization problems are amenable to optimization and yield estimators whose statistical behavior is well studied. When the outputs are not reals but higher dimensional, vector-valued Reproducible Kernel Hilbert Spaces (vv-RKHSs) based on Operator-Valued Kernels (OVKs) provide similarly powerful spaces of functions, and have proven useful to tackle problems such as multi-task learning, structured prediction, or function-valued regression.In this thesis, we introduce an original functional extension of multi-output learning called Infinite Task Learning (ITL), that ...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
The aim of this thesis is to systematically investigate some functional regression models for accura...
Learning mappings between infinite-dimensional function spaces has achieved empirical success in man...
Les méthodes à noyaux sont au coeur de l'apprentissage statistique. Elles permettent de modéliser de...
The increased availability of large amounts of data, from images in social networks, speech waveform...
The first part of this thesis aims at exploring deep kernel architectures for complex data. One of t...
L'apprentissage automatique a reçu beaucoup d'attention au cours des deux dernières décennies, à ...
Many problems in Machine Learning can be cast into vector-valued approximation. Operator-Valued Kern...
We extend the kernel based learning framework to learning from linear functionals, such as partial d...
The paper studies convex stochastic optimization problems in a reproducing kernel Hilbert space (RKH...
We consider the supervised learning problem when both covariates and responses are real functions ra...
We consider the problem of supervised learning with convex loss functions and propose a new form of ...
Estimating a set of orthogonal functions from a finite set of noisy data plays a crucial role in sev...
This thesis presents my main research activities in statistical machine learning aftermy PhD, starti...
This paper addresses the problem of choosing a kernel suitable for estimation with a support vector...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
The aim of this thesis is to systematically investigate some functional regression models for accura...
Learning mappings between infinite-dimensional function spaces has achieved empirical success in man...
Les méthodes à noyaux sont au coeur de l'apprentissage statistique. Elles permettent de modéliser de...
The increased availability of large amounts of data, from images in social networks, speech waveform...
The first part of this thesis aims at exploring deep kernel architectures for complex data. One of t...
L'apprentissage automatique a reçu beaucoup d'attention au cours des deux dernières décennies, à ...
Many problems in Machine Learning can be cast into vector-valued approximation. Operator-Valued Kern...
We extend the kernel based learning framework to learning from linear functionals, such as partial d...
The paper studies convex stochastic optimization problems in a reproducing kernel Hilbert space (RKH...
We consider the supervised learning problem when both covariates and responses are real functions ra...
We consider the problem of supervised learning with convex loss functions and propose a new form of ...
Estimating a set of orthogonal functions from a finite set of noisy data plays a crucial role in sev...
This thesis presents my main research activities in statistical machine learning aftermy PhD, starti...
This paper addresses the problem of choosing a kernel suitable for estimation with a support vector...
Large dimensional data and learning systems are ubiquitous in modern machine learning. As opposed to...
The aim of this thesis is to systematically investigate some functional regression models for accura...
Learning mappings between infinite-dimensional function spaces has achieved empirical success in man...