On concentration of self-bounding functions (2009)
Boucheron, Stephane; Université Paris-Diderot; Stephane.boucheron@math.jussieu.fr, Lugosi, Gabor; Pompeu Fabra University; Gabor.lugosi@gmail.com, Massart, Pascal; Université Paris-Sud; Pascal.massart@gmail.com
We prove some new concentration inequalities for self-bounding functions using the entropy method. As an application, we recover Talagrand's convex distance inequality. The new Bernstein-like...
Sharp threshold for percolation on expanders (2009)
Benjamini, Itai, Boucheron, Stephane, Lugosi, Gabor, Rossignol, Raphael
We study the appearance of the giant component in random subgraphs of a given finite graph G=(V,E) in which each edge is present independently with probability p. We show that if G is an expander...
Coding on countably infinite alphabets (2009)
Boucheron, Stephane, Gassiat, Elisabeth, Garivier, Aurelien
This paper describes universal lossless coding strategies for compressing sources on countably infinite alphabets. Classes of memoryless sources defined by an envelope condition on the marginal...
Yves Grandvalet, Stephane Boucheron
Noise Injection consists in adding noise to the inputs during neural network training. Experimental results suggest that it might improve the generalization ability of the resulting neural network. A...
Coding on Countably Infinite alphabets (2007)
Boucheron, Stephane, Garivier, Aurelien, Gassiat, Elisabeth
This paper describes universal lossless coding strategies for compressing sources on countably infinite alphabets. Classes of memoryless sources defined by an envelope condition on the marginal...
Coding on countably infinite alphabets (2006)
Boucheron, Stephane, Garivier, Aurelien, Gassiat, Elisabeth
This paper describes universal lossless coding strategies for compressing sources on countably infinite alphabets. Classes of memoryless sources defined by an envelope condition on the marginal...
Error exponents in AR order testing (2006)
Boucheron, Stephane, Gassiat, Elisabeth
This paper is concerned with error exponents in testing problems raised by autoregressive (\textsc{ar}) modeling. The tests to be considered are variants of generalized likelihood ratio testing...
Error exponents for AR order testing (2006)
Gassiat, Elisabeth, Boucheron, Stephane
This paper is concerned with error exponents in testing problems raised by auto-regressive (\textsc{ar}) modeling. The tests to be considered are variants of generalized likelihood ratio testing...
Coding on countably infinite alphabets (2006)
Boucheron, Stephane, Gassiat, Elisabeth, Garivier, Aurelien
This paper describes universal lossless coding strategies for compressing sources on countably infinite alphabets. Classes of memoryless sources defined by an envelope condition on the marginal...
Theory of classification: some recent advances (2005)
Boucheron, Stephane, Bousquet, Olivier, Lugosi, Gábor
The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have lead to these important...
Order estimation in Inference in Hidden Markov Models (2005)
Boucheron, Stephane, Gassiat, Elisabeth
This chapter is concerned with order identification and model selection problems in Hidden Markov modelling
Moment inequalities for functions of independent random variables (2005)
Boucheron, Stephane, Bousquet, Olivier, Lugosi, Gabor, Massart, Pascal
A general method for obtaining moment inequalities for functions of independent random variables is presented. It is a generalization of the entropy method which has been used to derive concentration...
Moment inequalities for functions of independent random variables. (2005)
Boucheron, Stephane, Bousquet, Olivier, Lugosi, Gábor, Massart, Pascal
A general method for obtaining moment inequalities for functions of independent random variables is presented. It is a generalization of the entropy method which has been used to derive concentration...
Concentration inequalities (2004)
Boucheron, Stephane, Bousquet, Olivier, Lugosi, Gábor
Concentration inequalities deal with deviations of functions of independent random variables from their expectation. In the last decade new tools have been introduced making it possible to establish...
Statistical Learning Theory (2004)
Bousquet, Olivier, Boucheron, Stephane, Lugosi, Gábor
The goal of statistical learning theory is to study, in a statistical framework, the properties of learning algorithms. In particular, most results take the form of so-called error bounds. This...
Theory of classification: some recent advances (2004)
Bousquet, Olivier, Boucheron, Stephane, Lugosi, Gábor
The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have lead to these important...
Moment inequalities for functions of independent random variables (2004)
Massart, Pascal, Boucheron, Stephane, LOGOSI, Gabor
A general method for obtaining moment inequalities for functions of independent random variables is presented. It is a generalization of the entropy method which has been used to derive concentration...
Optimal Error Exponents in Hidden Markov Models Order Estimation (2003)
Gassiat, Elisabeth, Boucheron, Stephane
We consider the estimation of the number of hidden states (the {order) of a discrete-time finite alphabet Hidden Markov Model (HMM). The estimators we investigate are related to code-based order...
Concentration inequalities using the entropy method (2003)
Boucheron, Stephane, Massart, Pascal, LUGOSI, Gabor
We investigate a new methodology, worked out by Ledoux and Massart,to prove concentration-of-measure inequalities. The method is based on certain modified logarithmic Sobolev inequalities. We provide...
Stephane Boucheron, Gabor Lugosi, Ramon Trias Fargas, Pascal Massart
We present a new general concentration-of-measure inequality and illustrate its power by applications in random combinatorics. The results nd direct applications in some problems of learning theory.