Skip to content
InfoResearchPeer-reviewed

A Unified Approach to Analysis and Design of Denoising Markov Models

Published
Record updated
View JSON

Summary

This paper sets out a mathematical foundation for denoising Markov models, a class of generative models pairing a forward process from the target distribution to a simple distribution with a constructed backward process for sampling. Using connections to nonequilibrium statistical mechanics and generalized Doob's h-transform, the authors give a unified variational objective and a recipe for designing such models driven by arbitrary Lévy-type processes. They demonstrate novel models using geometric Brownian motion and jump processes as forward dynamics.