Lipschitz Parametrization of Probabilistic Graphical Models
read the original abstract
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the Kullback-Leibler divergence that allows understanding methods that penalize the lp-norm of differences of parameters as the minimization of that upper bound. The expected log-likelihood is lower bounded by the negative lp-norm, which allows understanding the generalization ability of probabilistic models. The exponential of the negative lp-norm is involved in the lower bound of the Bayes error rate, which shows that it is reasonable to use parameters as features in algorithms that rely on metric spaces (e.g. classification, dimensionality reduction, clustering). Our results do not rely on specific algorithms for learning the structure or parameters. We show preliminary results for activity recognition and temporal segmentation.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Bayesian Regularization of Gaussian Graphical Models with Measurement Error
Proposes a Bayesian spike-and-slab Lasso method combined with imputation-regularization optimization to estimate sparse precision matrices in Gaussian graphical models while correcting for measurement error.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.