ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2312.08153
53
1

ρρρ-Diffusion: A diffusion-based density estimation framework for computational physics

13 December 2023
Maxwell X. Cai
Kin Long Kelvin Lee
    DiffM
ArXiv (abs)PDFHTML
Abstract

In physics, density ρ(⋅)\rho(\cdot)ρ(⋅) is a fundamentally important scalar function to model, since it describes a scalar field or a probability density function that governs a physical process. Modeling ρ(⋅)\rho(\cdot)ρ(⋅) typically scales poorly with parameter space, however, and quickly becomes prohibitively difficult and computationally expensive. One promising avenue to bypass this is to leverage the capabilities of denoising diffusion models often used in high-fidelity image generation to parameterize ρ(⋅)\rho(\cdot)ρ(⋅) from existing scientific data, from which new samples can be trivially sampled from. In this paper, we propose ρ\rhoρ-Diffusion, an implementation of denoising diffusion probabilistic models for multidimensional density estimation in physics, which is currently in active development and, from our results, performs well on physically motivated 2D and 3D density functions. Moreover, we propose a novel hashing technique that allows ρ\rhoρ-Diffusion to be conditioned by arbitrary amounts of physical parameters of interest.

View on arXiv
Comments on this paper