Pith. sign in

REVIEW 1 cited by

Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching

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 2206.08265 v2 pith:5WU56GDY submitted 2022-06-16 stat.ML cs.LG

classification stat.MLcs.LG
keywords scorelikelihoodmatchingscore-baseddiffusiondatahigh-ordermaximum
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Score-based generative models have excellent performance in terms of generation quality and likelihood. They model the data distribution by matching a parameterized score network with first-order data score functions. The score network can be used to define an ODE ("score-based diffusion ODE") for exact likelihood evaluation. However, the relationship between the likelihood of the ODE and the score matching objective is unclear. In this work, we prove that matching the first-order score is not sufficient to maximize the likelihood of the ODE, by showing a gap between the maximum likelihood and score matching objectives. To fill up this gap, we show that the negative likelihood of the ODE can be bounded by controlling the first, second, and third-order score matching errors; and we further present a novel high-order denoising score matching method to enable maximum likelihood training of score-based diffusion ODEs. Our algorithm guarantees that the higher-order matching error is bounded by the training error and the lower-order errors. We empirically observe that by high-order score matching, score-based diffusion ODEs achieve better likelihood on both synthetic data and CIFAR-10, while retaining the high generation quality.

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. MonoPartNeRF:Human Reconstruction from Monocular Video via Part-Based Neural Radiance Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Randomized weak measurements provide a physically motivated forward diffusion for quantum states, with reverse recovery via learned unitary controls, Petz maps, or classical shadows.

Pith tools