27 citations · 54 across the 18 of their papers we have counts for
24 papers
Pointwise convergence of purely random partition estimators: from random trees to prototype rules
Jérémy Bettinger, François Portier, Adrien Saumard
We study pointwise convergence rates of purely random partition estimators in nonparametric regression, where the partition -- into hyper-rectangles by purely random trees, or into…
Riemannian Stochastic Optimization for Sufficient Dimension Reduction
Thibault Pautrel, François Portier
Sufficient dimension reduction (SDR) makes high-dimensional regression tractable by projecting the covariates onto a low-dimensional subspace that preserves the conditional mean of…
Concentration and excess risk bounds for imbalanced classification with synthetic oversampling
Touqeer Ahmad, Mohammadreza M. Kalan, François Portier +1
Synthetic oversampling of minority examples using SMOTE and its variants is a leading strategy for addressing imbalanced classification problems. Despite the success of this approa…
Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
Rémi Leluc, Aymeric Dieuleveut, François Portier +2
The Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein distances resulting for the associated one-dimensional projections. A…
Nearest Neighbor Sampling for Covariate Shift Adaptation
François Portier, Lionel Truquet, Ikko Yamane
Many existing covariate shift adaptation methods estimate sample weights given to loss values to mitigate the gap between the source and the target distribution. However, estimatin…
Speeding up Monte Carlo Integration: Control Neighbors for Optimal Convergence
Rémi Leluc, François Portier, Johan Segers +1
A novel linear integration rule called is proposed in which nearest neighbor estimates act as control variates to speed up the convergence rate of the…
A Quadrature Rule combining Control Variates and Adaptive Importance Sampling
Rémi Leluc, François Portier, Johan Segers +1
Driven by several successful applications such as in stochastic gradient descent or in Bayesian computation, control variates have become a major tool for Monte Carlo integration.…
On the bias of K-fold cross validation with stable learners
Anass Aghbalou, François Portier, Anne Sabourin
This paper investigates the efficiency of the K-fold cross-validation (CV) procedure and a debiased version thereof as a means of estimating the generalization risk of a learning a…
Nearest neighbor empirical processes
François Portier
In the regression framework, the empirical measure based on the responses resulting from the nearest neighbors, among the covariates, to a given point is introduced and studied…
Tail inverse regression for dimension reduction with extreme response
Anass Aghbalou, François Portier, Anne Sabourin +1
We consider the problem of supervised dimension reduction with a particular focus on extreme values of the target to be explained by a covariate vector $X \in \mat…
Individual Survival Curves with Conditional Normalizing Flows
Guillaume Ausset, Tom Ciffreo, Francois Portier +2
Survival analysis, or time-to-event modelling, is a classical statistical problem that has garnered a lot of interest for its practical use in epidemiology, demographics or actuari…
SGD with Coordinate Sampling: Theory and Practice
Rémi Leluc, François Portier
While classical forms of stochastic gradient descent algorithm treat the different coordinates in the same way, a framework allowing for adaptive (non uniform) coordinate sampling…
Risk bounds when learning infinitely many response functions by ordinary linear regression
Vincent Plassier, François Portier, Johan Segers
Consider the problem of learning a large number of response functions simultaneously based on the same input variables. The training data consist of a single independent random sam…
Asymptotic Analysis of Conditioned Stochastic Gradient Descent
Rémi Leluc, François Portier
In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction. Using a…
Empirical Risk Minimization under Random Censorship: Theory and Practice
Guillaume Ausset, Stéphan Clémençon, François Portier
We consider the classic supervised learning problem, where a continuous non-negative random label (i.e. a random duration) is to be predicted based upon observing a random vect…
Control variate selection for Monte Carlo integration
Rémi Leluc, François Portier, Johan Segers
Monte Carlo integration with variance reduction by means of control variates can be implemented by the ordinary least squares estimator for the intercept in a multiple linear regre…
Parametric versus nonparametric: the fitness coefficient
Gildas Mazo, François Portier
The fitness coefficient, introduced in this paper, results from a competition between parametric and nonparametric density estimators within the likelihood of the data. As illustra…
Asymptotic optimality of adaptive importance sampling
Bernard Delyon, François Portier
Adaptive importance sampling (AIS) uses past samples to update the \textit{sampling policy} at each stage . Each stage is formed with two steps : (i) to explore the sp…
Monte Carlo integration with a growing number of control variates
François Portier, Johan Segers
It is well known that Monte Carlo integration with variance reduction by means of control variates can be implemented by the ordinary least squares estimator for the intercept in a…
On the weak convergence of the empirical conditional copula under a simplifying assumption
François Portier, Johan Segers
When the copula of the conditional distribution of two random variables given a covariate does not depend on the value of the covariate, two conflicting intuitions arise about the…
Efficiency of Z-estimators indexed by the objective functions
François Portier
We study the convergence of -estimators for which the objective function depends on a parameter that belongs to a Banach space . O…
Continuous inverse regression
François Portier
We provide new theoretical results in the field of inverse regression methods for dimension reduction. Our approach is based on the study of some empirical processes that lie close…
Integral approximation by kernel smoothing
Bernard Delyon, François Portier
Let be an i.i.d. sequence of random variables in , . We show that, for any function , under regularit…
On the acceleration of some empirical means with application to nonparametric regression
Bernard Delyon, François Portier
Let be an i.i.d. sequence of random variables in , , for some function , under regularity conditions, we show that \begin{align*} n^…