The topics addressed in this thesis lie in statistical machine learning. Our main framework is the prediction of arbitrary deterministic sequences (or individual sequences). It includes online learning tasks for which we cannot make any stochasticity assumption on the data to be predicted, which requires robust methods. In this work, we analyze several connections between the theory of individual sequences and the classical statistical setting, e.g., the regression model with fixed or random design, where stochastic assumptions are made. These two frameworks benefit from one another: some statistical methods can be adapted to the online learning setting to satisfy deterministic performance guarantees. Conversely, some individual-sequence te...
Many modern machine learning algorithms, though successful, are still based on heuristics. In a typi...
Machine learning algorithms are celebrated for their impressive performance on many tasksthat we tho...
Learning stochastic models generating sequences has many applications in natural language processing...
Cette thèse s'inscrit dans le domaine de l'apprentissage statistique. Le cadre principal est celui d...
Cette thèse s'inscrit dans le domaine de l'apprentissage statistique. Le cadre principal est celui d...
We consider the problem of online linear regression on arbitrary deterministic sequences when the am...
Directeur: Gabor LUGOSI President: Sylvain SORIN Membres du jury: Pascal MASSART, Nicolo CESA-BIANCH...
We present methods for online linear optimization that take advantage of benign (as opposed to worst...
Le domaine de recherche dans lequel s'inscrit ce travail de thèse est la théorie de la prédiction de...
This thesis works mainly on three subjects. The first one is online clustering in which we introduce...
First, we study online learning with an extended notion of regret, which is defined with respect to ...
The increasing size of available data has led machine learning specialists to consider more complex ...
First, we study online learning with an extended notion of regret, which is defined with respect to ...
In this document, we give an overview of recent contributions to the mathematics of statistical sequ...
In recent years, we have witnessed an increasing cross-fertilization between the fields of computer ...
Many modern machine learning algorithms, though successful, are still based on heuristics. In a typi...
Machine learning algorithms are celebrated for their impressive performance on many tasksthat we tho...
Learning stochastic models generating sequences has many applications in natural language processing...
Cette thèse s'inscrit dans le domaine de l'apprentissage statistique. Le cadre principal est celui d...
Cette thèse s'inscrit dans le domaine de l'apprentissage statistique. Le cadre principal est celui d...
We consider the problem of online linear regression on arbitrary deterministic sequences when the am...
Directeur: Gabor LUGOSI President: Sylvain SORIN Membres du jury: Pascal MASSART, Nicolo CESA-BIANCH...
We present methods for online linear optimization that take advantage of benign (as opposed to worst...
Le domaine de recherche dans lequel s'inscrit ce travail de thèse est la théorie de la prédiction de...
This thesis works mainly on three subjects. The first one is online clustering in which we introduce...
First, we study online learning with an extended notion of regret, which is defined with respect to ...
The increasing size of available data has led machine learning specialists to consider more complex ...
First, we study online learning with an extended notion of regret, which is defined with respect to ...
In this document, we give an overview of recent contributions to the mathematics of statistical sequ...
In recent years, we have witnessed an increasing cross-fertilization between the fields of computer ...
Many modern machine learning algorithms, though successful, are still based on heuristics. In a typi...
Machine learning algorithms are celebrated for their impressive performance on many tasksthat we tho...
Learning stochastic models generating sequences has many applications in natural language processing...