2024/09/14 by Stefano Peluchetti, Peluchetti, Stefano · 4 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Geophysical Methods and Applications #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Sparse and Compressive Sensing Techniques
paper · pdf · doi:10.48550/arxiv.2409.09376
openalex publication_date 2024/09/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A Schrödinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target distributions are available, and the reference diffusion process admits tractable dynamics. We thus introduce Coupled Bridge Matching (BM2), a simple non-iterative approach for learning Schrödinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM2 is carried out, supported by numerical experiments that demonstrate the effectiveness of our proposal.