AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

A Statistical Benchmark for Diffusion Posterior Sampling Algorithms

Martin Zach, Youssef Haouchat, Michael Unser

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hamiltonian Monte Carlo · 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
replace learned denoiser with oracle Gibbs denoiser (ablation)DPnP · Imputation, Student-t(1) jumpsMMSE optimality gap (dB): -10.46 ± 5.70Improved
replace learned denoiser with oracle Gibbs denoiser (ablation)DPnP · Deconvolution, Student-t(1) jumpsMMSE optimality gap (dB): -4.98 ± 3.86Improved
replace learned denoiser with oracle Gibbs denoiser (ablation)DiffPIR · Deconvolution, Student-t(1) jumpsMMSE optimality gap (dB): 13.56 ± 9.90Hurt
replace learned denoiser with oracle Gibbs denoiser (ablation)C-DPS · Deconvolution, Student-t(1) jumpsMMSE optimality gap (dB): 6.64 ± 3.21Hurt
replace learned denoiser with oracle Gibbs denoiser (ablation)C-DPS · Imputation, Student-t(1) jumpsMMSE optimality gap (dB): 3.41 ± 4.99Hurt
replace learned denoiser with oracle Gibbs denoiser (ablation)DPnP · Denoising, Gaussian jumpsMMSE optimality gap (dB): 0.04 ± 0.27No clear effect
replace learned denoiser with oracle Gibbs denoiser (ablation)DiffPIR · Denoising, Gaussian jumpsMMSE optimality gap (dB): 0.00 ± 0.13No clear effect
replace learned denoiser with oracle Gibbs denoiser (ablation)DPnP · Fourier, Student-t(1) jumpsMMSE optimality gap (dB): -1.32 ± 3.18Improved
replace learned denoiser with oracle Gibbs denoiser (ablation)DPnP · Denoising, Bernoulli-Laplace(0.1, 1) jumpsMMSE optimality gap (dB): -0.55 ± 1.31Improved
replace learned denoiser with oracle Gibbs denoiser (ablation)C-DPS · Imputation, Bernoulli-Laplace(0.1, 1) jumpsMMSE optimality gap (dB): 0.41 ± 1.51Hurt
add brief hand-tuning of DiffPIR parameters (zeta=0.7, rho=4) on the validation set (ablation)DiffPIR with oracle denoiser · Heavy-tailed jumpsMMSE optimality gap (dB): almost 10 dB lowerImproved
use DiffPIR instead of C-DPSDPS algorithms · Denoising, Bernoulli-Laplace(0.1, 1) jumpsMMSE optimality gap (dB): 2.22 -> 0.72Improved

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