Paper Share: Tsallis Regularized Optimal Transport and Ecological Inference

FrnkNlsn · x · 2026-08-08

Recommends a classic paper on Optimal Transport (OT). While discrete OT is computationally expensive, regularizing mass transport with a Shannon entropic term allows for fast numerical computations via the Sinkhorn balancing algorithm.

The paper proposes Tsallis Regularized Optimal Transport (TROT), which unifies the two main approaches to OT (Monge-Kantorovitch and Sinkhorn-Cuturi) into a single framework. TROT interpolates a rich family of distortions from Wasserstein to Kullback-Leibler divergence. It also presents the first application of OT to ecological inference, reconstructing joint distributions from their marginals.

Original post →

More from Research

Research channel →