This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statistical learning, (2) the three aggregation problems: given d functions, how to predict as well as (i) the best of these d functions (model selection type aggregation), (ii) the best convex combination of these d functions, (iii) the best linear combination of these d functions, (3) the multi-armed bandit problems
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learni...
We consider the problem of predicting as well as the best linear combination of d given functions in...
International audienceWe study the issue of PAC-Bayesian domain adaptation: We want to learn, from a...
This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statisti...
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random vari...
This thesis is devoted to the study of both theoretical and practical properties of various aggregat...
Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their ...
This thesis is devoted to the study of both theoretical and practicalproperties of various aggregati...
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learn...
International audienceWe provide a first PAC-Bayesian analysis for domain adaptation (DA) which aris...
International audienceThis paper provides a theoretical analysis of domain adaptation based on the P...
National audienceIn this work on regression with Gaussian error, we study an agregation procedure re...
We study the problem of selecting K arms with the highest expected rewards in a stochastic N-armed b...
The two-armed bandit problem is a classical optimization problem where a player sequentially selects...
University of Minnesota Ph.D. dissertation. July 2014. Major: Statistics. Advisor: Yuhong Yang. 1 co...
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learni...
We consider the problem of predicting as well as the best linear combination of d given functions in...
International audienceWe study the issue of PAC-Bayesian domain adaptation: We want to learn, from a...
This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statisti...
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random vari...
This thesis is devoted to the study of both theoretical and practical properties of various aggregat...
Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their ...
This thesis is devoted to the study of both theoretical and practicalproperties of various aggregati...
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learn...
International audienceWe provide a first PAC-Bayesian analysis for domain adaptation (DA) which aris...
International audienceThis paper provides a theoretical analysis of domain adaptation based on the P...
National audienceIn this work on regression with Gaussian error, we study an agregation procedure re...
We study the problem of selecting K arms with the highest expected rewards in a stochastic N-armed b...
The two-armed bandit problem is a classical optimization problem where a player sequentially selects...
University of Minnesota Ph.D. dissertation. July 2014. Major: Statistics. Advisor: Yuhong Yang. 1 co...
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learni...
We consider the problem of predicting as well as the best linear combination of d given functions in...
International audienceWe study the issue of PAC-Bayesian domain adaptation: We want to learn, from a...
Add to ORKG