
TL;DR
This paper leverages Lie group symmetry to derive explicit solutions for optimal transport problems on group orbits, unifying and extending known results to new distribution families.
Contribution
It formalizes the role of symmetry via Lie groups in solving optimal transport problems, providing explicit solutions for certain distribution classes.
Findings
Closed-form solutions for optimal transport on Lie group orbits.
Unified framework for elliptical, Wishart, inverse-Wishart, and matrix beta distributions.
Structural criteria for transport maps with positive definite linear parts.
Abstract
In its most general form, the optimal transport problem is an infinite-dimensional optimization problem, yet certain notable instances admit closed-form solutions. We identify the common source of this tractability as \textit{symmetry} and formalize it using Lie group theory. Fixing a Lie group action on the outcome space and a reference distribution, we study optimal transport between measures lying on the same Lie group orbit of the reference distribution. In this setting, the Monge problem admits an explicit upper bound given by an optimization problem over the stabilizer subgroup of the reference distribution. The reduced problem's dimension scales with that of the stabilizing subgroup and, in the tractable cases we study, is either zero or finite. Under mild regularity conditions, a feasible point of this reduced problem whose induced transport map satisfies a -convex…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
