activity
20182022
most citedSecureFedYJ: a safe feature Gaussianization protocol for Federated Learning

3 citations · 5 across the 2 of their papers we have counts for

collaborators

8 papers

cs.LG20223 cited

SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning

Tanguy Marchand, Boris Muzellec, Constance Beguier +2

The Yeo-Johnson (YJ) transformation is a standard parametrized per-feature unidimensional transformation often used to Gaussianize features in machine learning. In this paper, we i…

cs.LG20212 cited

A Note on Optimizing Distributions using Kernel Mean Embeddings

Boris Muzellec, Francis Bach, Alessandro Rudi

Kernel mean embeddings are a popular tool that consists in representing probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. Wh…

math.ST2021

A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation

Adrien Vacher, Boris Muzellec, Alessandro Rudi +2

It is well-known that plug-in statistical estimation of optimal transport suffers from the curse of dimensionality. Despite recent efforts to improve the rate of estimation with th…

math.ST2020

Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form

Hicham Janati, Boris Muzellec, Gabriel Peyré +1

Although optimal transport (OT) problems admit closed form solutions in a very few notable cases, e.g. in 1D or between Gaussians, these closed forms have proved extremely fecund f…

math.PR2020

Dimension-free convergence rates for gradient Langevin dynamics in RKHS

Boris Muzellec, Kanji Sato, Mathurin Massias +1

Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable attention lately, as a way to provide convergence guarantees in a non-convex setting. However…

stat.ML2020

Missing Data Imputation using Optimal Transport

Boris Muzellec, Julie Josse, Claire Boyer +1

Missing data is a crucial issue when applying machine learning algorithms to real-world datasets. Starting from the simple assumption that two batches extracted randomly from the s…