activity
20112026
most citedInfinite-dimensional gradient-based descent for alpha-divergence minimisation

11 citations · 18 across the 18 of their papers we have counts for

collaborators

18 papers

math.ST2026

A uniform relative deviation inequality for VC-subgraph classes

François Portier

We establish a new Bernstein-type deviation inequality for classes of functions whose complexity is characterized through subgraphs. The inequality is non-asymptotic, involves expl…

math.ST2026

Revisiting local regression: shape regularity, uniform rates, and the limits of random splits

Jérémy Bettinger, François Portier, Adrien Saumard

Considering pointwise and sup-norm estimation, we analyze the non-asymptotic behavior of local averaging estimators for Lipschitz regression functions. Building on a general deviat…

math.OC2026

Importance Sampling Optimization with Laplace Principle

Radu-Alexandru Dragomir, François Portier, Victor Priser

Grid search and random search are widely used techniques for hyperparameter tuning in machine learning, especially when gradient information is unavailable. In these methods, a fin…

math.ST2025

On the pointwise and sup-norm errors for local regression estimators

Jérémy Bettinger, François Portier, Adrien Saumard

In this paper, we analyze the behavior of various non-parametric local regression estimators, i.e. estimators that are based on local averaging, for estimating a Lipschitz regressi…

math.ST2025

A theory of shape regularity for local regression maps

Jérémy Bettinger, François Portier, Adrien Saumard

We introduce the concept of shape-regular regression maps as a framework to derive optimal rates of convergence for various non-parametric local regression estimators. Using Vapnik…

math.ST2024★ 1 cited

Stochastic mirror descent for nonparametric adaptive importance sampling

Pascal Bianchi, Bernard Delyon, Victor Priser +1

This paper addresses the problem of approximating an unknown probability distribution with density -- which can only be evaluated up to an unknown scaling factor -- with the he…

math.ST2024

Logistic lasso regression with nearest neighbors for gradient-based dimension reduction

Touqeer Ahmad, François Portier, Gilles Stupfler

This paper investigates a new approach to estimate the gradient of the conditional probability given the covariates in the binary classification framework. The proposed approach co…

math.ST2022

High-dimensional nonconvex lasso-type -estimators

Jad Beyhum, François Portier

This paper proposes a theory for -norm penalized high-dimensional -estimators, with nonconvex risk and unrestricted domain. Under high-level conditions, the estimators a…

math.ST2021★ 1 cited

Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff

Anna Korba, François Portier

Adaptive importance sampling is a widely spread Monte Carlo technique that uses a re-weighting strategy to iteratively estimate the so-called target distribution. A major drawback…

cs.LG2020★ 2 cited

Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications

Guillaume Ausset, Stephan Clémençon, François Portier

Motivated by a wide variety of applications, ranging from stochastic optimization to dimension reduction through variable selection, the problem of estimating gradients accurately…

stat.ME2020★ 1 cited

Conditional independence testing via weighted partial copulas and nearest neighbors

Pascal Bianchi, Kevin Elgui, François Portier

This paper introduces the \textit{weighted partial copula} function for testing conditional independence. The proposed test procedure results from these two ingredients: (i) the te…

math.ST2020★ 11 cited

Infinite-dimensional gradient-based descent for alpha-divergence minimisation

Kamélia Daudel, Randal Douc, François Portier

This paper introduces the -descent, an iterative algorithm which operates on measures and performs -divergence minimisation in a Bayesian framework. This gradient-based…

math.ST2019

High dimensional regression for regenerative time-series: an application to road traffic modeling

Mohammed Bouchouia, François Portier

A statistical predictive model in which a high-dimensional time-series regenerates at the end of each day is used to model road traffic. Due to the regeneration, prediction is base…

math.ST2019

The -Divergence Expectation Iteration Scheme

Kamélia Daudel, Randal Douc, François Portier +1

This paper introduces the -EI algorithm, a novel iterative algorithm which operates on measures and performs -divergence minimisation in a Bayesian framework. We prove t…

math.ST2018★ 1 cited

Rademacher complexity for Markov chains : Applications to kernel smoothing and Metropolis-Hasting

Patrice Bertail, François Portier

Following the seminal approach by Talagrand, the concept of Rademacher complexity for independent sequences of random variables is extended to Markov chains. The proposed notion of…

math.ST2018★ 1 cited

On an extension of the promotion time cure model

François Portier, Ingrid Van Keilegom, Anouar El Ghouch

We consider the problem of estimating the distribution of time-to-event data that are subject to censoring and for which the event of interest might never occur, i.e., some subject…

math.ST2013

Bootstrap Testing of the Rank of a Matrix via Least Squared Constrained Estimation

François Portier, Bernard Delyon

In order to test if an unknown matrix has a given rank (null hypothesis), we consider the family of statistics that are minimum squared distances between an estimator and the manif…

math.ST2011

Test function: A new approach for covering the central subspace

François Portier, Bernard Delyon

In this paper we offer a complete methodology for sufficient dimension reduction called the test function (TF). TF provides a new family of methods for the estimation of the centra…