M
Marco Cuturi
Researcher at Google
Publications - 155
Citations - 12954
Marco Cuturi is an academic researcher from Google. The author has contributed to research in topics: Computer science & Metric (mathematics). The author has an hindex of 42, co-authored 141 publications receiving 9403 citations. Previous affiliations of Marco Cuturi include École Normale Supérieure & Mines ParisTech.
Papers
More filters
Proceedings Article
Semigroup Kernels on Finite Sets
Marco Cuturi,Jean-Philippe Vert +1 more
TL;DR: A general integral representation of positive definite (p.d.) kernels for two such objects that can be expressed as a function of the merger of their respective sets of components is proved.
Proceedings Article
Wasserstein regularization for sparse multi-task regression
TL;DR: A convex regularizer for multi-task regression that encodes a more flexible geometry based on unbalanced optimal transport (OT) theory, and can take into account a prior geometric knowledge on the regressor variables, without necessarily requiring overlapping supports.
Proceedings ArticleDOI
Supervised Training of Conditional Monge Maps
TL;DR: C OND OT is introduced, an approach to estimate OT maps conditioned on a context variable, using several pairs of measures tagged with a context label c i to infer the effect of an arbitrary combination of genetic or therapeutic perturbation on single cells, using only observations of the effects of said perturbations separately.
Journal ArticleDOI
Information Geometry for Regularized Optimal Transport and Barycenters of Patterns
TL;DR: A new divergence on the manifold of probability distributions is proposed, building on the entropic regularization of optimal transportation problems, that is able to retain key intuitive aspects of the Wasserstein geometry, such as translation invariance, and admits an intuitive interpretation.
Posted Content
On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests
TL;DR: In this article, the Wasserstein distance is used to connect different types of nonparametric two-sample testing, including PP/QQQ plots and ROC/ODC curves.