No AI summary available for this article.
Why It Matters
Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be pulled back to clean-space posteriors with weaker conditioning, with samples transported analytically to the corresponding noisy-space target through a Gaussian bridge. For the sequential Monte Carlo (SMC) sampler MCGDiff, the effective observation variance of this pulled-back problem is up to twice the diffusion-noise variance. We exploit this structure to initialize MCGDiff directly at an intermediate time: an approximate solver samples the so...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.06834v1 · Indexed about 1 hour ago