pith. sign in

Z T 0 1 2 ∥ut(Xt)−σ t∇logP ∗ T|t (XT |Xt)∥2dt # .(36) Finally, we obtain theweighted denoising cross entropyoptimization problem: u∗ = argmin u EX∼P ∗

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Proximal Diffusion Neural Sampler

cs.LG · 2025-10-04 · unverdicted · novelty 6.0

PDNS decomposes diffusion neural sampler training into proximal subproblems on path measures to gradually approach multimodal targets and promote mode exploration.

citing papers explorer

Showing 1 of 1 citing paper.

  • Proximal Diffusion Neural Sampler cs.LG · 2025-10-04 · unverdicted · none · ref 6

    PDNS decomposes diffusion neural sampler training into proximal subproblems on path measures to gradually approach multimodal targets and promote mode exploration.