Pith. sign in

REVIEW 5 cited by

Memorization and Regularization in Generative Diffusion Models

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 2501.15785 v2 pith:U6YWBZOS submitted 2025-01-27 cs.LG math.DSmath.OC

Memorization and Regularization in Generative Diffusion Models

classification cs.LG math.DSmath.OC
keywords regularizationmemorizationdatagenerativeminimizerscoreanalysisanalytically
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Diffusion models have emerged as a powerful framework for generative modeling. At the heart of the methodology is score matching: learning gradients of families of log-densities for noisy versions of the data distribution at different scales. When the loss function adopted in score matching is evaluated using empirical data, rather than the population loss, the minimizer corresponds to the score of a time-dependent Gaussian mixture. However, use of this analytically tractable minimizer leads to data memorization: in both unconditioned and conditioned settings, the generative model returns the training samples. This paper contains an analysis of the dynamical mechanism underlying memorization. The analysis highlights the need for regularization to avoid reproducing the analytically tractable minimizer; and, in so doing, lays the foundations for a principled understanding of how to regularize. Numerical experiments investigate the properties of: (i) Tikhonov regularization; (ii) regularization designed to promote asymptotic consistency; and (iii) regularizations induced by under-parameterization of a neural network or by early stopping when training a neural network. These experiments are evaluated in the context of memorization, and directions for future development of regularization are highlighted.

discussion (0)

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

Forward citations

Cited by 5 Pith papers

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

  1. Tessellations of Semi-Discrete Flow Matching

    cs.LG 2026-05 unverdicted novelty 7.0

    Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Lagu...

  2. On The Hidden Biases of Flow Matching Samplers

    stat.ML 2025-12 unverdicted novelty 7.0

    Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlli...

  3. Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

    cs.LG 2026-06 unverdicted novelty 6.0

    Introduces the Invariant Contamination Ratio (ICR), a Fisher-based metric, to evaluate how diffusion models balance invariant representations with residual variation and to detect the onset of memorization during training.

  4. On the Memorization of Consistency Distillation for Diffusion Models

    cs.LG 2026-04 unverdicted novelty 6.0

    Consistency distillation reduces memorization in diffusion models by suppressing unstable feature directions associated with memorization while preserving stable generalizable modes.

  5. Conditional flow matching for physics-constrained inverse problems with finite training data

    stat.ML 2026-03 unverdicted novelty 6.0

    Conditional flow matching learns a velocity field to sample from measurement-conditioned posteriors in physics inverse problems, with early stopping to prevent variance collapse and selective memorization under finite...