AI RESEARCH
Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates
arXiv CS.LG
•
ArXi:2605.30722v1 Announce Type: new We propose CerT-MCMC, a framework that equips learned-transport Marko chain Monte Carlo with automatic, rigorous convergence certificates. A normalising flow maps a Gaussian reference to an approximation of the target posterior; the same flow then serves as both the independence Metropolis-Hastings proposal and the basis for a computable spectral-gap bound. We develop two complementary certificates.