Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

By Luhuan Wu, Brian L. Trippe, C. A. Naesseth, David M. Blei, John P. Cunningham. 2023

230 citations recorded by the source corpus.

Diffusion models have been successful on a range of conditional generation tasks including molecular design and text-to-image generation. However, these achievements have primarily depended on task-specific conditional training or error-prone heuristic approximations. Ideally, a conditional generation method should provide exact samples for a broad range of conditional distributions without requiring task-specific training. To this end, we introduce the Twisted Diffusion Sampler, or TDS. TDS is a sequential Monte Carlo (SMC) algorithm that targets the conditional distributions of diffusion models through simulating a set of weighted particles. The main idea is to use twisting, an SMC technique that enjoys good computational efficiency, to incorporate heuristic approximations without compromising asymptotic exactness. We first find in simulation and in conditional image generation tasks that TDS provides a computational statistical trade-off, yielding more accurate approximations with many particles but with empirical improvements over heuristics with as few as two particles. We then turn to motif-scaffolding, a core task in protein design, using a TDS extension to Riemannian diffusion models. On benchmark test cases, TDS allows flexible conditioning criteria and often outperforms the state of the art.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

  1. Rohith Krishna
  2. Jue Wang
  3. Ivan V. Anishchenko
  4. Minkyung Baek
  5. Woody Ahern
  6. Ryan McHugh
  7. Pascal Sturmfels
  8. Indrek Kalvet

Citations in the corpus