Control Consistency Losses for Diffusion Bridges
Authors
Samuel Howard, Nikolas Nüsken, Jakiw Pidstrigach
Categories
Abstract
Simulating the conditioned dynamics of diffusion processes, given their initial and terminal states, is an important but challenging problem in the sciences. The difficulty is particularly pronounced for rare events, for which the unconditioned dynamics rarely reach the terminal state. In this work, we leverage a self-consistency property of the conditioned dynamics to learn the diffusion bridge in an iterative online manner, and demonstrate promising empirical results in a range of settings.
Control Consistency Losses for Diffusion Bridges
Categories
Abstract
Simulating the conditioned dynamics of diffusion processes, given their initial and terminal states, is an important but challenging problem in the sciences. The difficulty is particularly pronounced for rare events, for which the unconditioned dynamics rarely reach the terminal state. In this work, we leverage a self-consistency property of the conditioned dynamics to learn the diffusion bridge in an iterative online manner, and demonstrate promising empirical results in a range of settings.
Authors
Samuel Howard, Nikolas Nüsken, Jakiw Pidstrigach
Click to preview the PDF directly in your browser