technique

diffusion posterior sampling

techniqueactiveprovisionaldiffusion-posterior-sampling-f3e6e0be·1 events·first seen 19d ago

Aliases: diffusion posterior sampling

Co-occurring entities

finite-sample posterior sampling framework likelihood approximation imaging inverse problems Diffusion Models

More like this (12)

finite-sample posterior sampling framework discrete diffusion models diffusion-based inpainting LESS: Mutual-Stability Sampling for Diffusion Language Models Denoising Diffusion Probabilistic Models Masked Diffusion Models latent diffusion model Survival Diffusion Probabilistic Model (SDPM)Gibbs-Accelerated Discrete Diffusion (GADD)Representation-Conditioned Diffusion Models diffusion-based policy diffusion-based generative models

Recent events (1)

6arXiv · cs.LG·19d ago·source ↗

Finite-Sample Lens for Understanding Diffusion Posterior Sampler Failures

This paper introduces a finite-sample theoretical framework for analyzing diffusion model posterior samplers used in imaging inverse problems. The authors show that popular likelihood approximations at intermediate timesteps systematically under- or over-estimate posterior spread, leading to failure modes including sensitivity to early stopping, incorrect weighting of posterior modes, and hallucination of prior or likelihood modes. Crucially, they demonstrate these failures can arise from a multimodal prior alone, without requiring nonlinear measurement models or multimodal posteriors. The framework is model-agnostic and can serve as a diagnostic tool for evaluating existing and future posterior samplers.

Evaluation and Benchmarking AI Safety Research finite-sample posterior sampling framework likelihood approximation imaging inverse problems +3 more