Generalized score matching for general domains
From MaRDI portal
Abstract: Estimation of density functions supported on general domains arises when the data is naturally restricted to a proper subset of the real space. This problem is complicated by typically intractable normalizing constants. Score matching provides a powerful tool for estimating densities with such intractable normalizing constants, but as originally proposed is limited to densities on and . In this paper, we offer a natural generalization of score matching that accommodates densities supported on a very general class of domains. We apply the framework to truncated graphical and pairwise interaction models, and provide theoretical guarantees for the resulting estimators. We also generalize a recently proposed method from bounded to unbounded domains, and empirically demonstrate the advantages of our method.
Recommendations
Cited in
(6)- Some extensions of score matching
- Estimation of non-normalized statistical models by score matching
- Generalized score matching for non-negative data
- Optimal convex M-estimation via score matching
- Stein's method of moments
- Score matching for differential abundance testing of compositional high-throughput sequencing data
This page was built for publication: Generalized score matching for general domains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095268)