Adrien Saumard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Adrien Saumard has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jon A. Wellner
University of Washington
4 shared publications - Erwan Hillion
Aix Marseille Univ, CNRS, I2M Marseille, France
1 shared publication - Fabien Navarro
Fabien Navarro CREST ENSAI France
1 shared publication - Oliver Johnson
University of Bristol
1 shared publication
Latest Publications
- 5 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 67 (10) , 6328-6343
Finite Sample Improvement of Akaike’s Information Criterion
Considering the selection of frequency histograms, we propose a modification of Akaike’s Information Criterion that avoids overfitting, even when the sample size is small. We call this correction an over-penalization procedure. We emphasize that the principle of unbiased risk estimation for model selection can indeed be improved by addressing excess risk deviations in the design of the penalization procedure. On the theoretical side, we prove sharp oracle inequalities for the Kullback-Leibler divergence. These inequalities are valid with positive probability for any sample size and include the estimation of unbounded log-densities. Along the proofs, we derive several analytical lemmas related to the Kullback-Leibler divergence, as well as concentration inequalities, that are of independent interest. In a simulation study, we also demonstrate state-of-the-art performance of our over-penalization criterion for bin size selection, in particular outperforming AICc procedure.
- 5 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 67 (10) , 6328-6343
Finite Sample Improvement of Akaike’s Information Criterion
Considering the selection of frequency histograms, we propose a modification of Akaike’s Information Criterion that avoids overfitting, even when the sample size is small. We call this correction an over-penalization procedure. We emphasize that the principle of unbiased risk estimation for model selection can indeed be improved by addressing excess risk deviations in the design of the penalization procedure. On the theoretical side, we prove sharp oracle inequalities for the Kullback-Leibler divergence. These inequalities are valid with positive probability for any sample size and include the estimation of unbounded log-densities. Along the proofs, we derive several analytical lemmas related to the Kullback-Leibler divergence, as well as concentration inequalities, that are of independent interest. In a simulation study, we also demonstrate state-of-the-art performance of our over-penalization criterion for bin size selection, in particular outperforming AICc procedure.
- Open Access
- 25 September 2018
- Published by Elsevier in Statistics & Probability Letters
- Vol. 145, 181-186
An extremal property of the normal distribution, with a discrete analog
- 25 September 2018
- Published by Elsevier in Statistics & Probability Letters
- Vol. 145, 181-186
Open AccessAn extremal property of the normal distribution, with a discrete analog
- Open Access
On the isoperimetric constant, covariance inequalities and $L_p$-Poincaré inequalities in dimension one
Firstly, we derive in dimension one a new covariance inequality of $L_{1}-L_{\infty}$ type that characterizes the isoperimetric constant as the best constant achieving the inequality. Secondly, we generalize our result to $L_{p}-L_{q}$ bounds for the covariance. Consequently, we recover Cheeger's inequality without using the co-area formula. We also prove a generalized weighted Hardy type inequality that is needed to derive our covariance inequalities and that is of independent interest. Finally, we explore some consequences of our covariance inequalities for $L_{p}$-Poincar\'{e} inequalities and moment bounds. In particular, we obtain optimal constants in general $L_{p}$-Poincar\'{e} inequalities for measures with finite isoperimetric constant, thus generalizing in dimension one Cheeger's inequality, which is a $L_{p}$-Poincar\'{e} inequality for $p=2$, to any real $p\geq 1$.Open AccessOn the isoperimetric constant, covariance inequalities and $L_p$-Poincaré inequalities in dimension one
Firstly, we derive in dimension one a new covariance inequality of $L_{1}-L_{\infty}$ type that characterizes the isoperimetric constant as the best constant achieving the inequality. Secondly, we generalize our result to $L_{p}-L_{q}$ bounds for the covariance. Consequently, we recover Cheeger's inequality without using the co-area formula. We also prove a generalized weighted Hardy type inequality that is needed to derive our covariance inequalities and that is of independent interest. Finally, we explore some consequences of our covariance inequalities for $L_{p}$-Poincar\'{e} inequalities and moment bounds. In particular, we obtain optimal constants in general $L_{p}$-Poincar\'{e} inequalities for measures with finite isoperimetric constant, thus generalizing in dimension one Cheeger's inequality, which is a $L_{p}$-Poincar\'{e} inequality for $p=2$, to any real $p\geq 1$. - Open AccessEfron's monotonicity property for measures on $\mathbb{R}^2$First we prove some kernel representations for the covariance of two functions taken on the same random variable and deduce kernel representations for some functionals of a continuous one-dimensional measure. Then we apply these formulas to extend Efron's monotonicity property, given in Efron [1965] and valid for independent log-concave measures, to the case of general measures on $\mathbb{R}^2$. The new formulas are also used to derive some further quantitative estimates in Efron's monotonicity property.Open AccessEfron's monotonicity property for measures on $\mathbb{R}^2$First we prove some kernel representations for the covariance of two functions taken on the same random variable and deduce kernel representations for some functionals of a continuous one-dimensional measure. Then we apply these formulas to extend Efron's monotonicity property, given in Efron [1965] and valid for independent log-concave measures, to the case of general measures on $\mathbb{R}^2$. The new formulas are also used to derive some further quantitative estimates in Efron's monotonicity property.
- Open Access
Log-concavity and strong log-concavity: a review
We review and formulate results concerning log-concavity and strong-log-concavity in both discrete and continuous settings. We show how preservation of log-concavity and strongly log-concavity on $\mathbb{R}$ under convolution follows from a fundamental monotonicity result of Efron (1969). We provide a new proof of Efron's theorem using the recent asymmetric Brascamp-Lieb inequality due to Otto and Menz (2013). Along the way we review connections between log-concavity and other areas of mathematics and statistics, including concentration of measure, log-Sobolev inequalities, convex geometry, MCMC algorithms, Laplace approximations, and machine learning.Open AccessLog-concavity and strong log-concavity: a review
We review and formulate results concerning log-concavity and strong-log-concavity in both discrete and continuous settings. We show how preservation of log-concavity and strongly log-concavity on $\mathbb{R}$ under convolution follows from a fundamental monotonicity result of Efron (1969). We provide a new proof of Efron's theorem using the recent asymmetric Brascamp-Lieb inequality due to Otto and Menz (2013). Along the way we review connections between log-concavity and other areas of mathematics and statistics, including concentration of measure, log-Sobolev inequalities, convex geometry, MCMC algorithms, Laplace approximations, and machine learning. - Top Cited PapersOpen Access
- 1 January 2014
- Published by Institute of Mathematical Statistics in Statistics Surveys
- Vol. 8 (none) , 45-114
Log-concavity and strong log-concavity: A review
We review and formulate results concerning log-concavity and strong-log-concavity in both discrete and continuous settings. We show how preservation of log-concavity and strong log-concavity on $\mathbb{R}$ under convolution follows from a fundamental monotonicity result of Efron (1965). We provide a new proof of Efron’s theorem using the recent asymmetric Brascamp-Lieb inequality due to Otto and Menz (2013). Along the way we review connections between log-concavity and other areas of mathematics and statistics, including concentration of measure, log-Sobolev inequalities, convex geometry, MCMC algorithms, Laplace approximations, and machine learning.- 1 January 2014
- Published by Institute of Mathematical Statistics in Statistics Surveys
- Vol. 8 (none) , 45-114
Top Cited PapersOpen AccessLog-concavity and strong log-concavity: A review
We review and formulate results concerning log-concavity and strong-log-concavity in both discrete and continuous settings. We show how preservation of log-concavity and strong log-concavity on $\mathbb{R}$ under convolution follows from a fundamental monotonicity result of Efron (1965). We provide a new proof of Efron’s theorem using the recent asymmetric Brascamp-Lieb inequality due to Otto and Menz (2013). Along the way we review connections between log-concavity and other areas of mathematics and statistics, including concentration of measure, log-Sobolev inequalities, convex geometry, MCMC algorithms, Laplace approximations, and machine learning.