Adapted optimal transport between Gaussian processes in discrete time
Madhu Gunasingam, Ting-Kam Leonard Wong

TL;DR
This paper introduces an explicit formulation of the adapted 2-Wasserstein distance for Gaussian distributions, providing a new bicausal coupling characterization and an adapted Bures-Wasserstein distance for positive definite matrices.
Contribution
It derives an explicit form of the adapted 2-Wasserstein distance between Gaussian distributions and characterizes the optimal bicausal couplings, extending the Bures-Wasserstein distance.
Findings
Explicit formula for adapted 2-Wasserstein distance between Gaussians
Characterization of optimal bicausal couplings
Extension to adapted Bures-Wasserstein distance
Abstract
We derive explicitly the adapted -Wasserstein distance between non-degenerate Gaussian distributions on and characterize the optimal bicausal coupling(s). This leads to an adapted version of the Bures-Wasserstein distance on the space of positive definite matrices.
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.
Taxonomy
TopicsRandom Matrices and Applications · Markov Chains and Monte Carlo Methods · Statistical Mechanics and Entropy
