45 citations · 204 across the 11 of their papers we have counts for
13 papers
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…
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers +21
Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models, without centralizing data. The cross-s…
Near-optimal estimation of smooth transport maps with kernel sums-of-squares
Boris Muzellec, Adrien Vacher, Francis Bach +2
It was recently shown that under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error up…
Learning PSD-valued functions using kernel sums-of-squares
Boris Muzellec, Francis Bach, Alessandro Rudi
Shape constraints such as positive semi-definiteness (PSD) for matrices or convexity for functions play a central role in many applications in machine learning and sciences, includ…
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…
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…
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…
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…
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…
Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
Boris Muzellec, Marco Cuturi
Computing optimal transport (OT) between measures in high dimensions is doomed by the curse of dimensionality. A popular approach to avoid this curse is to project input measures o…
Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
Boris Muzellec, Marco Cuturi
Embedding complex objects as vectors in low dimensional spaces is a longstanding problem in machine learning. We propose in this work an extension of that approach, which consists…
Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances
Frank Nielsen, Boris Muzellec, Richard Nock
We consider the supervised classification problem of machine learning in Cayley-Klein projective geometries: We show how to learn a curved Mahalanobis metric distance corresponding…
Tsallis Regularized Optimal Transport and Ecological Inference
Boris Muzellec, Richard Nock, Giorgio Patrini +1
Optimal transport is a powerful framework for computing distances between probability distributions. We unify the two main approaches to optimal transport, namely Monge-Kantorovitc…