arXiv Analytics

Sign in

arXiv:1205.2629 [cs.LG]AbstractReferencesReviewsResources

Interpretation and Generalization of Score Matching

Siwei Lyu

Published 2012-05-09Version 1

Score matching is a recently developed parameter learning method that is particularly effective to complicated high dimensional density models with intractable partition functions. In this paper, we study two issues that have not been completely resolved for score matching. First, we provide a formal link between maximum likelihood and score matching. Our analysis shows that score matching finds model parameters that are more robust with noisy training data. Second, we develop a generalization of score matching. Based on this generalization, we further demonstrate an extension of score matching to models of discrete data.

Comments: Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009)
Categories: cs.LG, stat.ML
Related articles: Most relevant | Search more
arXiv:2011.05348 [cs.LG] (Published 2020-11-10)
SALR: Sharpness-aware Learning Rates for Improved Generalization
arXiv:1904.08129 [cs.LG] (Published 2019-04-17)
Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning
arXiv:2107.02658 [cs.LG] (Published 2021-07-06)
On Generalization of Graph Autoencoders with Adversarial Training