REVIEW 4 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
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.
Forward citations
Cited by 4 Pith papers
-
When and how can inexact generative models still sample from the data manifold?
Inexact generative models stay on the data manifold because infinitesimal learning errors perturb the density only along the manifold, when top Lyapunov vectors align with the support boundary.
-
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
In one-dimensional denoising score matching with two-layer ReLU networks, a large SGD learning rate provably prevents the learned score from getting close to the empirical optimal score, mitigating memorization.
-
PAC-DP: PAC-Bayesian Diffusion Policy Learning
Adding a PAC-Bayes KL regularizer to Bayesian diffusion policies improves denoising, likelihood bounds, and robotic success rates most in low-data and complex tasks.
-
A Kinetic Energy Perspective of Flow Matching
A per-sample kinetic-energy score along flow-matching trajectories tracks semantic quality and data rarity, with an extreme-energy regime that predicts memorization, and a two-phase inference-time shaping that improve...
Discussion (0). Continue with ORCID to comment.