Pith. sign in

REVIEW 1 cited by

What's the score? Automated Denoising Score Matching for Nonlinear Diffusions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.07998 v1 pith:4F7B2N6Y submitted 2024-07-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords scorediffusionprocessesnonlinearautomatedautomated-dsmbuiltdenoising
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear processes with a Gaussian stationary distribution. This limits the kinds of models that can be built to those that target a Gaussian prior or more generally limits the kinds of problems that can be generically solved to those that have conditionally linear score functions. In this work, we introduce a family of tractable denoising score matching objectives, called local-DSM, built using local increments of the diffusion process. We show how local-DSM melded with Taylor expansions enables automated training and score estimation with nonlinear diffusion processes. To demonstrate these ideas, we use automated-DSM to train generative models using non-Gaussian priors on challenging low dimensional distributions and the CIFAR10 image dataset. Additionally, we use the automated-DSM to learn the scores for nonlinear processes studied in statistical physics.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Reduced-Order Modeling of Cyclo-Stationary Time Series Using Score-Based Generative Methods

    nlin.CD 2025-08 conditional novelty 4.0 of 10

    A score-based generative model with an annual-cycle phase coordinate reproduces cyclo-stationary climate statistics from 20 principal components of a PlaSim simulation.

Pith tools