Timezone: »

 
Poster
Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
Boris Muzellec · Marco Cuturi

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #17
in Algorithms -- Nonlinear Dimensionality Reduction and Manifold Learning »

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 on lower-dimensional subspaces (1D lines in the case of sliced Wasserstein distances), solve the OT problem between these reduced measures, and settle for the Wasserstein distance between these reductions, rather than that between the original measures. This approach is however difficult to extend to the case in which one wants to compute an OT map (a Monge map) between the original measures. Since computations are carried out on lower-dimensional projections, classical map estimation techniques can only produce maps operating in these reduced dimensions. We propose in this work two methods to extrapolate, from an transport map that is optimal on a subspace, one that is nearly optimal in the entire space. We prove that the best optimal transport plan that takes such "subspace detours" is a generalization of the Knothe-Rosenblatt transport. We show that these plans can be explicitly formulated when comparing Gaussian measures (between which the Wasserstein distance is commonly referred to as the Bures or Fréchet distance). We provide an algorithm to select optimal subspaces given pairs of Gaussian measures, and study scenarios in which that mediating subspace can be selected using prior information. We consider applications to semantic mediation between elliptic word embeddings and domain adaptation with Gaussian mixture models.

Keywords: Nonlinear Dimensionality Reduction and Manifold Learning · Generative Models · Algorithms · Algorithms -> Components Analysis (e.g., CCA, ICA, LDA, PCA); Deep Learning
[ Paper]  [ Slides] 

Author Information

Boris Muzellec (ENSAE, Institut Polytechnique de Paris)
Marco Cuturi (Google Brain & CREST - ENSAE)

Marco Cuturi is a research scientist at Apple, in Paris. He received his Ph.D. in 11/2005 from the Ecole des Mines de Paris in applied mathematics. Before that he graduated from National School of Statistics (ENSAE) with a master degree (MVA) from ENS Cachan. He worked as a post-doctoral researcher at the Institute of Statistical Mathematics, Tokyo, between 11/2005 and 3/2007 and then in the financial industry between 4/2007 and 9/2008. After working at the ORFE department of Princeton University as a lecturer between 2/2009 and 8/2010, he was at the Graduate School of Informatics of Kyoto University between 9/2010 and 9/2016 as a tenured associate professor. He joined ENSAE in 9/2016 as a professor, where he is now working part-time. He was at Google between 10/2018 and 1/2022. His main employment is now with Apple, since 1/2022, as a research scientist working on fundamental aspects of machine learning.

More from the Same Authors