technique

likelihood approximation

techniqueactiveprovisionallikelihood-approximation-cea4e9b1·1 events·first seen 19d ago

Aliases: likelihood approximation

Co-occurring entities

finite-sample posterior sampling framework imaging inverse problems diffusion posterior sampling Diffusion Models

More like this (12)

rank-1 approximation reward-induced maximum likelihood Universal Approximation Theorem Maximum Likelihood Estimation Log Probability Bias Analysis finite-sample posterior sampling framework A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise amortized variational inference latent reasoning Representational Similarity Analysis linear representation hypothesis adaptive-rank instantiation

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