April 10, 2024
On the convergence of approximate Schrödinger Bridge – Location-SC 1320
The Schrödinger bridge has demonstrated promising applications in generative models. It is an entropy-regularized optimal-transport (EOT) approach that employs the iterative proportional fitting (IPF) algorithm to solve an alternating projection problem. However, due to the complexity of finding precise solutions for the projections, approximations are often required. In our study, we study the convergence of the IPF algorithm using approximated projections with a bounded cost or on a bounded domain. Our results demonstrate an approximate linear convergence with bounded perturbations. This is a joint work with Wei Deng, Yu Chen, Nicole Tianjiao Yang, Qi Feng, and Ricky TQ Chen.