Measuring Effective Data Resolution in Guided Diffusion Posteriors

arXiv:2610.04422v1 Announce Type: new Abstract: Guided diffusion samplers are increasingly used to reconstruct physical fields from sparse observations, but standard diagnostics do not say how much of the reconstruction was actually determined by the data. We introduce effective data resolution for black-box generative posteriors: a comparison between the resolution warranted by the inverse problem, dof_{ref}, and the resolution realised by the sampler, dof_{samp}. A perturbation estimator measures dof_{samp} and the spatial map R(x,x) from sampler queries alone. We validate the estimator against exact references and use it to study guided diffusion. The resulting measurements show that guidance weight can strongly alter apparent information transfer, that mean, spread and resolution are not jointly corrected by one weight even with an exact prior and score, and that resolution fidelity does not follow reliably from the apparent principledness of a guidance rule.

Related

• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• When, why, and how do diffusion posterior samplers fail? A finite-sample lens
• HarmoCore: Functional Latent Diffusion for Sparse Reconstruction of Oscillatory Wave Fields
• Physical-State-Guided Diffusion Sampling for Full-Waveform Inversion
• Tempered Guided Diffusion

Source: arXiv cs.LG | 2026-10-06