REVIEW 7 cited by
Generative diffusion model with inverse renormalization group flows
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
Generative diffusion model with inverse renormalization group flows
read the original abstract
Diffusion models represent a class of generative models that produce data by denoising a sample corrupted by white noise. Despite the success of diffusion models in computer vision, audio synthesis, and point cloud generation, so far they overlook inherent multiscale structures in data and have a slow generation process due to many iteration steps. In physics, the renormalization group offers a fundamental framework for linking different scales and giving an accurate coarse-grained model. Here we introduce a renormalization group-based diffusion model that leverages multiscale nature of data distributions for realizing a high-quality data generation. In the spirit of renormalization group procedures, we define a flow equation that progressively erases data information from fine-scale details to coarse-grained structures. Through reversing the renormalization group flows, our model is able to generate high-quality samples in a coarse-to-fine manner. We validate the versatility of the model through applications to protein structure prediction and image generation. Our model consistently outperforms conventional diffusion models across standard evaluation metrics, enhancing sample quality and/or accelerating sampling speed by an order of magnitude. The proposed method alleviates the need for data-dependent tuning of hyperparameters in the generative diffusion models, showing promise for systematically increasing sample efficiency based on the concept of the renormalization group.
Forward citations
Cited by 7 Pith papers
-
The critical slowing down in diffusion models
Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling.
-
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
SKILD unifies unconditional image generation and continuous super-resolution in one diffusion model via scale-invariant k-space dynamics where the reverse process handles both tasks by varying only the starting timestep.
-
Functional Renormalization for Signal Detection: Dimensional Analysis and Dimensional Phase Transition for Nearly Continuous Spectra Effective Field Theory
Functional renormalization group applied to nearly continuous spectra yields a scale-dependent canonical dimension that undergoes a dimensional phase transition at signal-to-noise ratios below the BBP threshold, corre...
-
Diffusion Models for Sampling Near Criticality in Lattice Field Theories
Fully convolutional diffusion models trained on small lattices transfer to unseen larger volumes for 2D/3D phi^4 sampling across phases, matching or beating same-size training on most observables.
-
The critical slowing down in diffusion models
Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.
-
Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization
Global Annealing Monte Carlo with ML global moves plus local updates outperforms Simulated Annealing and is more robust than Population Annealing on 3D Ising spin glasses without hyperparameter tuning.
-
Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection
Flicker-DDPM accelerates DDPM sampling by injecting 1/f colored noise matched to image spectra, achieving similar quality with 3.33 times fewer steps on CIFAR-10.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.