arXiv Open Access 2025

Sparse Data Diffusion for Scientific Simulations in Biology and Physics

Phil Ostheimer Mayank Nagda Andriy Balinskyy Jean Radig Carl Herrmann +3 lainnya
Lihat Sumber

Abstrak

Sparse data is fundamental to scientific simulations in biology and physics, from single-cell gene expression to particle calorimetry, where exact zeros encode physical absence rather than weak signal. However, existing diffusion models lack the physical rigor to faithfully represent this sparsity. This work introduces Sparse Data Diffusion (SDD), a generative method that explicitly models exact zeros via Sparsity Bits, unifying efficient ML generation with physically grounded sparsity handling. Empirical validation in particle physics and single-cell biology demonstrates that SDD achieves higher fidelity than baseline methods in capturing sparse patterns critical for scientific analysis, advancing scalable and physically faithful simulation.

Topik & Kata Kunci

Penulis (8)

P

Phil Ostheimer

M

Mayank Nagda

A

Andriy Balinskyy

J

Jean Radig

C

Carl Herrmann

S

Stephan Mandt

M

Marius Kloft

S

Sophie Fellenz

Format Sitasi

Ostheimer, P., Nagda, M., Balinskyy, A., Radig, J., Herrmann, C., Mandt, S. et al. (2025). Sparse Data Diffusion for Scientific Simulations in Biology and Physics. https://arxiv.org/abs/2502.02448

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓