CORE MACHINE LEARNING

Riemannian Convex Potential Maps

July 18, 2021

Abstract

Modeling distributions on Riemannian manifolds is a crucial component in understanding non-Euclidean data that arises, e.g., in physics and geology. The budding approaches in this space are limited by representational and computational tradeoffs. We propose and study a class of flows that uses convex potentials from Riemannian optimal transport. These are universal and can model distributions on any compact Riemannian manifold without requiring domain knowledge of the manifold to be integrated into the architecture. We demonstrate that these flows can model standard distributions on spheres, and tori, on synthetic and geological data.

Download the Paper

AUTHORS

Written by

Samuel Cohen

Brandon Amos

Yaron Lipman

Publisher

ICML 2021

Research Topics

Core Machine Learning

Related Publications

November 03, 2020

CORE MACHINE LEARNING

Robust Embedded Deep K-means Clustering

Rui Zhang, Hanghang Tong Yinglong Xia, Yada Zhu

November 03, 2020

December 03, 2020

CORE MACHINE LEARNING

Adversarial Example Games

Pascal Vincent, Hugo Berard, Andre Cianflone, Gauthier Gidel, Joey Bose, Simon Lacoste-Julien, Will Hamilton

December 03, 2020

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.