
LinearTime Gromov Wasserstein Distances using Low Rank Couplings and Costs
The ability to compare and align related datasets living in heterogeneou...
read it

Efficient and Modular Implicit Differentiation
Automatic differentiation (autodiff) has revolutionized machine learning...
read it

LowRank Sinkhorn Factorization
Several recent applications of optimal transport (OT) theory to machine ...
read it

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification
Optimal transport (OT) distances are increasingly used as loss functions...
read it

Projection Robust Wasserstein Distance and Riemannian Optimization
Projection robust Wasserstein (PRW) distance, or Wasserstein projection ...
read it

Handling Multiple Costs in Optimal Transport: Strong Duality and Efficient Computation
We introduce an extension of the optimal transportation (OT) problem whe...
read it

Linear Time Sinkhorn Divergences using Positive Features
Although Sinkhorn divergences are now routinely used in data sciences to...
read it

Debiased Sinkhorn barycenters
Entropy regularization in optimal transport (OT) has been the driver of ...
read it

Noisy Adaptive Group Testing using Bayesian Sequential Experimental Design
When test resources are scarce, a viable alternative to test for the pre...
read it

Learning with Differentiable Perturbed Optimizers
Machine learning pipelines often rely on optimization procedures to make...
read it

Revisiting Fixed Support Wasserstein Barycenter: Computational Hardness and Efficient Algorithms
We study the fixedsupport Wasserstein barycenter problem (FSWBP), whic...
read it

FixedSupport Wasserstein Barycenters: Computational Hardness and Fast Algorithm
We study the fixedsupport Wasserstein barycenter problem (FSWBP), whic...
read it

Computational Hardness and Fast Algorithm for FixedSupport Wasserstein Barycenter
We study in this paper the fixedsupport Wasserstein barycenter problem ...
read it

Regularized Optimal Transport is Ground Cost Adversarial
Regularizing Wasserstein distances has proved to be the key in the recen...
read it

Missing Data Imputation using Optimal Transport
Missing data is a crucial issue when applying machine learning algorithm...
read it

Supervised Quantile Normalization for Lowrank Matrix Approximation
Low rank matrix factorization is a fundamental building block in machine...
read it

Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces
The problem of comparing distributions endowed with their own geometry a...
read it

Ground Metric Learning on Graphs
Optimal transport (OT) distances between probability distributions are p...
read it

SpatioTemporal Alignments: Optimal transport through space and time
Comparing data defined over space and time is notoriously hard, because ...
read it

Multisubject MEG/EEG source imaging with sparse multitask regression
Magnetoencephalography and electroencephalography (M/EEG) are noninvasi...
read it

On the Complexity of Approximating Multimarginal Optimal Transport
We study the complexity of approximating the multimarginal optimal trans...
read it

Deep multiclass learning from label proportions
We propose a learning algorithm capable of learning from label proportio...
read it

Differentiable Sorting using Optimal Transport:The Sinkhorn CDF and Quantile Operator
Sorting an array is a fundamental routine in machine learning, one that ...
read it

Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal Transport
The problem of estimating Wasserstein distances in highdimensional spac...
read it

Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
read it

Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
Sliced Wasserstein metrics between probability measures solve the optima...
read it

Group level MEG/EEG source imaging via optimal transport: minimum Wasserstein estimates
Magnetoencephalography (MEG) and electroencephalography (EEG) are noni...
read it

TreeSliced Approximation of Wasserstein Distances
Optimal transport () theory provides a useful set of tools to compare pr...
read it

Subspace Robust Wasserstein distances
Making sense of Wasserstein distances between discrete measures in high...
read it

Stochastic Deep Networks
Machine learning is increasingly targeting areas where input data cannot...
read it

Semidual Regularized Optimal Transport
Variational problems that involve Wasserstein distances and more general...
read it

Unsupervised Hyperalignment for Multilingual Word Embeddings
We consider the problem of aligning continuous word representations, lea...
read it

Sample Complexity of Sinkhorn divergences
Optimal transport (OT) and maximum mean discrepancies (MMD) are now rout...
read it

Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport
Persistence diagrams (PDs) are now routinely used to summarize the under...
read it

Wasserstein regularization for sparse multitask regression
Two important elements have driven recent innovation in the field of reg...
read it

Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
Embedding complex objects as vectors in low dimensional spaces is a long...
read it

Computational Optimal Transport
Optimal Transport (OT) is a mathematical gem at the interface between pr...
read it

Wasserstein Dictionary Learning: Optimal Transportbased unsupervised nonlinear dictionary learning
This article introduces a new nonlinear dictionary learning method for ...
read it

Sliced Wasserstein Kernel for Persistence Diagrams
Persistence diagrams (PDs) play a key role in topological data analysis ...
read it

GAN and VAE from an Optimal Transport Point of View
This short article revisits some of the ideas introduced in arXiv:1701.0...
read it

Learning Generative Models with Sinkhorn Divergences
The ability to compare two degenerate probability distributions (i.e. tw...
read it

SoftDTW: a Differentiable Loss Function for TimeSeries
We propose in this paper a differentiable learning loss between time ser...
read it

Wasserstein Discriminant Analysis
Wasserstein Discriminant Analysis (WDA) is a new supervised method that ...
read it

On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests
Nonparametric two sample or homogeneity testing is a decision theoretic ...
read it

Wasserstein Training of Boltzmann Machines
The Boltzmann machine provides a useful framework to learn highly comple...
read it

Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric
Given a family of probability measures in P(X), the space of probability...
read it

Fast Optimal Transport Averaging of Neuroimaging Data
Knowing how the Human brain is anatomically and functionally organized a...
read it

A Smoothed Dual Approach for Variational Wasserstein Problems
Variational problems that involve Wasserstein distances have been recent...
read it

Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances
Optimal transportation distances are a fundamental family of parameteriz...
read it

Positivity and Transportation
We prove in this paper that the weighted volume of the set of integral t...
read it
Marco Cuturi
is this you? claim profile
Professor of Statistics in CREST  ENSAE at Université ParisSaclay, Ph.D. under the supervision of JeanPhilippe Vert in 11/2005 from the Ecole des Mines de Paris, Postdoctoral researcher at the Institute of Statistical Mathematics, Tokyo, between 11/2005 and 03/2007. ORFE department of Princeton University between 02/2009 and 08/2010 as a lecturer, I was at the Graduate School of Informatics of Kyoto University between 09/2010 and 09/2016 as an associate professor (tenured in 11/2013).