Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence

Abstract:Estimation of parameter of probabilistic models is an important task in the field of machine this http URL models of discrete variables, calculation of the normalization constant of model is sometimes difficult and a lot of researches have been done to avoid the calculation of the normalization constant. In this paper, we tackle with the difficulty by combining a technique of empirical localization and a deformed Bregman this http URL technique of empirical localization makes it possible to drastically reduce computational cost of the calculation of the normalization constant, and in addition, appropriate choice of the deformation for the Bregman divergence can invest the proposed estimator with various kinds of favorable statistical properties, such as efficiency or robustness against outlier noise.

Machine Learning (stat.ML); Machine Learning (cs.LG)

arXiv:2609.30713 [stat.ML]

(or arXiv:2609.30713v1 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2609.30713 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.