The reviewed record of science sign in
Pith

arxiv: 2202.07477 · v2 · pith:GCVKFP5S · submitted 2022-02-14 · stat.ML · cs.AI· cs.LG· cs.NA· math.AP· math.NA

Understanding DDPM Latent Codes Through Optimal Transport

Valentin Khrulkov , Gleb Ryzhakov , Andrei Chertkov , Ivan Oseledets This is my paper

Reviewed by Pithpith:GCVKFP5Sopen to challenge →

classification stat.ML cs.AIcs.LGcs.NAmath.APmath.NA
keywords ddpmdiffusionencoderlatentmodelsoptimaltransportaddress
0
0 comments X
read the original abstract

Diffusion models have recently outperformed alternative approaches to model the distribution of natural images, such as GANs. Such diffusion models allow for deterministic sampling via the probability flow ODE, giving rise to a latent space and an encoder map. While having important practical applications, such as estimation of the likelihood, the theoretical properties of this map are not yet fully understood. In the present work, we partially address this question for the popular case of the VP SDE (DDPM) approach. We show that, perhaps surprisingly, the DDPM encoder map coincides with the optimal transport map for common distributions; we support this claim theoretically and by extensive numerical experiments.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

    cs.LG 2022-09 unverdicted novelty 8.0

    Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.

  2. MeshFlow: Mesh Generation with Equivariant Flow Matching

    cs.GR 2026-06 unverdicted novelty 7.0

    MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.

  3. Generative diffusion learning for parametric partial differential equations

    math.NA 2023-05 unverdicted novelty 6.0

    A conditional DDPM framework is introduced to approximate solution operators for parameter-dependent PDEs, achieving accuracy comparable to FNO while recovering noise levels and providing confidence intervals.

  4. Rectified Flow: A Marginal Preserving Approach to Optimal Transport

    stat.ML 2022-09 unverdicted novelty 6.0

    A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.