paper-with-me

Papers

Generative diffusion model with inverse renormalization group flows

2025-01-15 · Kanta Masuki, Yuto Ashida

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.

📄 PDF Abstract BibTeX arXiv:2501.09064

Code (1)

kantamasuki/rgdm 공식 구현 pytorch

Tasks

Audio SynthesisDenoisingImage GenerationmodelPoint Cloud GenerationProtein Structure Prediction

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Renormalizing Diffusion Models

2023-08-23 · Jordan Cotler, Semon Rezchikov

We explain how to use diffusion models to learn inverse renormalization group flows of statistical and quantum field theories. Diffusion models are a class of machine learning models which have been used to generate samp…

The Inverse of Exact Renormalization Group Flows as Statistical Inference

2022-12-21 · David S. Berman, Marc S. Klinger

We build on the view of the Exact Renormalization Group (ERG) as an instantiation of Optimal Transport described by a functional convection-diffusion equation. We provide a new information theoretic perspective for under…

Bayesian Inference

Generating configurations of increasing lattice size with machine learning and the inverse renormalization group

2024-05-25 · Dimitrios Bachtis

We review recent developments of machine learning algorithms pertinent to the inverse renormalization group, which was originally established as a generative numerical method by Ron-Swendsen-Brandt via the implementation…

Neural Network Renormalization Group

2018-02-08 · Shuo-Hui Li, Lei Wang

We present a variational renormalization group (RG) approach using a deep generative model based on normalizing flows. The model performs hierarchical change-of-variables transformations from the physical space to a late…

Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

2020-01-02 · Gavin S. Hartnett, Masoud Mohseni

Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimization, inference in graphical models, and au…

Self-Supervised Learning