13 citations · 30 across the 11 of their papers we have counts for
11 papers
Geometry-induced Regularization in Deep ReLU Neural Networks
Joachim Bona-Pellissier, François Malgouyres, François Bachoc
Neural networks with a large number of parameters often do not overfit, owing to implicit regularization that favors \lq good\rq{} networks. Other related and puzzling phenomena in…
Selective inference after convex clustering with penalization
François Bachoc, Cathy Maugis-Rabusseau, Pierre Neuvial
Classical inference methods notoriously fail when applied to data-driven test hypotheses or inference targets. Instead, dedicated methodologies are required to obtain statistical g…
A generalization of the CIRCE method for quantifying input model uncertainty in presence of several groups of experiments
Guillaume Damblin, François Bachoc, Sandro Gazzo +2
The semi-empirical nature of best-estimate models closing the balance equations of thermal-hydraulic (TH) system codes is well-known as a significant source of uncertainty for accu…
Local Identifiability of Deep ReLU Neural Networks: the Theory
Joachim Bona-Pellissier, François Malgouyres, François Bachoc
Is a sample rich enough to determine, at least locally, the parameters of a neural network? To answer this question, we introduce a new local parameterization of a given deep ReLU…
Shapley effect estimation in reliability-oriented sensitivity analysis with correlated inputs by importance sampling
Julien Demange-Chryst, François Bachoc, Jérôme Morio
Reliability-oriented sensitivity analysis aims at combining both reliability and sensitivity analyses by quantifying the influence of each input variable of a numerical model on a…
Bounds in Wasserstein distance on the normal approximation of general M-estimators
François Bachoc, Max Fathi
We derive quantitative bounds on the rate of convergence in Wasserstein distance of general M-estimators, with an almost sharp (up to a logarithmic term) behavior in the numb…
Blind source separation for non-stationary random fields
Christoph Muehlmann, François Bachoc, Klaus Nordhausen
Regional data analysis is concerned with the analysis and modeling of measurements that are spatially separated by specifically accounting for typical features of such data. Namely…
Test of the Latent Dimension of a Spatial Blind Source Separation Model
Christoph Muehlmann, François Bachoc, Klaus Nordhausen +1
We assume a spatial blind source separation model in which the observed multivariate spatial data is a linear mixture of latent spatially uncorrelated Gaussian random fields contai…
Maximum likelihood estimation for Gaussian processes under inequality constraints
François Bachoc, Agnès Lagnoux, Andrés F. López-Lopera
We consider covariance parameter estimation for a Gaussian process under inequality constraints (boundedness, monotonicity or convexity) in fixed-domain asymptotics. We address the…
A supermartingale approach to Gaussian process based sequential design of experiments
Julien Bect, François Bachoc, David Ginsbourger
Gaussian process (GP) models have become a well-established frameworkfor the adaptive design of costly experiments, and notably of computerexperiments. GP-based sequential designs…
Improvement of code behaviour in a design of experiments by metamodeling
François Bachoc, Jean-Marc Martinez, Karim Ammar
It is now common practice in nuclear engineering to base extensive studies on numerical computer models. These studies require to run computer codes in potentially thousands of num…