Cost-augmented Schrödinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control

Paper recorded by Signals 4 on 2026-10-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-01 on arXiv · recorded by Signals 4 on 2026-10-02

Category: cs.LG · 机器学习 · first seen 2026-10-02

Abstract

The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached by learning the rates of a controlled continuous-time Markov chain, with a temporal-difference penalty that restores the cost. A state cost folds into the reference process as a Feynman-Kac tilt. The cost-augmented bridge is then a plain bridge aga

Read on arXiv →