Applying Regularized Schr\"odinger-Bridge-Based Stochastic Process in Generative Modeling

TL;DR

This paper introduces a regularized Schr"odinger-Bridge-based stochastic process to improve the efficiency of generative modeling by reducing sampling and training times while maintaining high-quality results.

Contribution

It proposes novel regularization terms for SB models that enable faster sampling and training, making stochastic process-based generative models more practical.

Findings

Achieved faster sampling speeds with fewer timesteps.

Reduced training time through regularization.

Successfully applied to various generation tasks.

Abstract

Compared to the existing function-based models in deep generative modeling, the recently proposed diffusion models have achieved outstanding performance with a stochastic-process-based approach. But a long sampling time is required for this approach due to many timesteps for discretization. Schr\"odinger bridge (SB)-based models attempt to tackle this problem by training bidirectional stochastic processes between distributions. However, they still have a slow sampling speed compared to generative models such as generative adversarial networks. And due to the training of the bidirectional stochastic processes, they require a relatively long training time. Therefore, this study tried to reduce the number of timesteps and training time required and proposed regularization terms to the existing SB models to make the bidirectional stochastic processes consistent and stable with a reduced number of timesteps. Each regularization term was integrated into a single term to enable more efficient training in computation time and memory usage. Applying this regularized stochastic process to various generation tasks, the desired translations between different distributions were obtained, and accordingly, the possibility of generative modeling based on a stochastic process with faster sampling speed could be confirmed. The code is available at https://github.com/KiUngSong/RSB.