Control, Transport and Sampling: The Benefit of a Reference Process
Abstract: We aim to establish connections between diffusion-based sampling, optimal transport, and optimal (stochastic) control through their shared links to the Schroedinger bridge problem. Throughout, we highlight the importance of having a reference measure on the path space for the design of a valid objective function that can be used to transport $\nu$ to $\mu$, consequently sample from the target $\mu$, via (optimally) controlled dynamics.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Valentin_De_Bortoli1
Submission Number: 1636
Loading