AI RESEARCH
Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
arXiv CS.LG
•
ArXi:2602.02045v2 Announce Type: replace Diffusion models have emerged as powerful learned priors for Bayesian inverse problems (BIPs). Diffusion-based solvers rely on a presumed likelihood for the observations in BIPs to guide the generation process. Likelihood misspecification is common in practical BIPs and is known to degrade recovery performance, particularly under outlier contamination. We investigate this problem by first characterizing the induced posterior deviation and proving the stability of diffusion-based solvers for linear BIPs.