March 5, 2024, 2:43 p.m. | Jhanvi Garg, Xianyang Zhang, Quan Zhou

cs.LG updates on arXiv.org arxiv.org

arXiv:2403.01717v1 Announce Type: cross
Abstract: Schr\"{o}dinger bridge can be viewed as a continuous-time stochastic control problem where the goal is to find an optimally controlled diffusion process with a pre-specified terminal distribution $\mu_T$. We propose to generalize this stochastic control problem by allowing the terminal distribution to differ from $\mu_T$ but penalizing the Kullback-Leibler divergence between the two distributions. We call this new control problem soft-constrained Schr\"{o}dinger bridge (SSB). The main contribution of this work is a theoretical derivation of …

abstract arxiv bridge continuous control cs.lg diffusion distribution math.oc process stat.co stat.ml stochastic terminal type

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Sr. BI Analyst

@ AkzoNobel | Pune, IN