Estimation of partially known Gaussian graphical models with score-based structural priors

arXiv:2401.14340v3 Announce Type: replace-cross
Abstract: We propose a novel algorithm for the support estimation of partially known Gaussian graphical models that incorporates prior information about the underlying graph. In contrast to classical approaches that provide a point estimate based on a maximum likelihood or a maximum a posteriori criterion using (simple) priors on the precision matrix, we consider a prior on the graph and rely on annealed Langevin diffusion to generate samples from the posterior distribution. Since the Langevin sampler …

abstract algorithm arxiv contrast criterion cs.lg graph information likelihood novel prior stat.ml support type