AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Sample-efficient evidence estimation of score based priors for model selection

Frederic Wang, Katherine Bouman

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use improved prior-aware posterior covariance instead of the sigma_t^2 heuristic in Gaussian-approximation DAPS (ablation)DiME · Gaussian mixture, in-distribution x*relative error (%): 146% -> 1.5%Improved
use improved covariance instead of original heuristic (ablation)DiME · Gaussian mixture, out-of-distribution x*relative error (%): 3.3% -> 0.3%Improved
use PnP-DM marginals (DiME-tilted) instead of standard DAPS marginals (ablation)DiME · Gaussian mixture, out-of-distribution x*relative error (%): 0.3% -> 13.8%Hurt
use PnP-DM marginals instead of standard marginals (ablation)DiME · Gaussian mixture, in-distribution x*relative error (%): 1.5% -> 2.4%No clear effect
estimate evidence along posterior time-marginals (DiME) instead of power-posterior SMCevidence estimator · Gaussian mixture, saddle point x*relative error (%): 0.7% -> 0.8%No clear effect
use DiME instead of naive Monte Carloevidence estimation · Gaussian mixture, in-distribution x*relative error (%): 2263% -> 1.5%Improved
use DiME instead of SMC with learned score as surrogate prior scoreMNIST diffusion priors, Gaussian and Fourier phase retrieval model selection · MNIST digit prior selectioncorrect model selectedImproved
use Gaussian-approximation DAPS instead of exact DAPS (ablation)DiME on M87* · M87* model selectioncompute time: 30 min -> 4 min (about 7x)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy