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
Generalized Aitchison Embeddings for Histograms
Tam Le,Marco Cuturi +1 more
TL;DR: In this article, the authors propose a new contribution to address this problem by generalizing a family of embeddings proposed by Aitchison (1982) to map the probability simplex onto a suitable Euclidean space.
Posted ContentDOI
LSMMD-MA: Scaling multimodal data integration for single-cell genomics data analysis
TL;DR: This work reformulates the MMD-MA optimization problem using linear algebra and solves it with KeOps, a CUDA framework for symbolic matrix computation in Python, and shows that LSMMD-MA scales to a million cells in each modality, two orders of magnitude greater than existing implementations.
Journal ArticleDOI
Unbalanced Low-rank Optimal Transport Solvers
TL;DR: In this paper , the authors propose a unified optimal transport method for the linear OT problem and its Fused-Gromov-Wasserstein generalization, and demonstrate their practical relevance to challenging spatial transcriptomics matching problems.
Posted Content
Low-Rank Sinkhorn Factorization
TL;DR: In this article, a generic approach is proposed to solve the optimal transport problem under low-rank constraints with arbitrary costs, which can be solved through the machinery of regularized 2-Wasserstein barycenters.
Posted Content
Kernels for Measures Defined on the Gram Matrix of their Support
TL;DR: A new family of kernels to compare positive measures on arbitrary spaces $\Xcal$ endowed with a positive kernel $\kappa$ is presented, which translates naturally into kernels between histograms or clouds of points.