Diffusion-HMC: Parameter Inference with Diffusion Model driven Hamiltonian Monte Carlo

arXiv:2405.05255v1 Announce Type: cross
Abstract: Diffusion generative models have excelled at diverse image generation and reconstruction tasks across fields. A less explored avenue is their application to discriminative tasks involving regression or classification problems. The cornerstone of modern cosmology is the ability to generate predictions for observed astrophysical fields from theory and constrain physical models from observations using these predictions. This work uses a single diffusion generative model to address these interlinked objectives -- as a surrogate model or emulator …

abstract application arxiv astro-ph.co classification cosmology cs.lg diffusion diffusion model diverse fields generate generative generative models hamiltonian monte carlo image image generation inference modern predictions regression tasks type