First non-asymptotic sample complexity bounds for structure learning of polynomial exponential families via score matching, with polynomial dependence on model dimension.
2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Polynomial-time algorithm recovers the conditional-independence graph of a d-sparse GGM from one Glauber trajectory with length independent of mixing time.
citing papers explorer
-
Finite Sample Bounds for Learning with Score Matching
First non-asymptotic sample complexity bounds for structure learning of polynomial exponential families via score matching, with polynomial dependence on model dimension.
-
Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing
Polynomial-time algorithm recovers the conditional-independence graph of a d-sparse GGM from one Glauber trajectory with length independent of mixing time.