Hybrid random fields are a recently proposed graphical model for pseudo-likelihood estimation in discrete domains. In this paper, we develop a continuous version of the model for nonparametric density estimation. To this aim, Nadaraya-Watson kernel estimators are used to model the local conditional densities within hybrid random fields. First, we introduce a heuristic algorithm for tuning the kernel bandwidhts in the conditional density estimators. Second, we propose a novel method for initializing the structure learning algorithm originally employed for hybrid random fields, which was meant instead for discrete variables. In order to test the accuracy of the proposed technique, we use a number of synthetic pattern classification benchmarks, generated from random distributions featuring nonlinear correlations between the variables. As compared to state-of-the-art nonparametric and semiparametric learning techniques for probabilistic graphical models, kernel-based hybrid random fields regularly outperform each considered alternative in terms of recognition accuracy, while preserving the scalability properties (with respect to the number of variables) that originally motivated their introduction.
Freno, A., Trentin, E., Gori, M. (2010). Kernel-based hybrid random fields for nonparametric density estimation. In ECAI 2010 - 19TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE (pp.427-432). Amsterdam : IOS-Press [10.3233/978-1-60750-606-5-427].
Kernel-based hybrid random fields for nonparametric density estimation
FRENO, ANTONINO;TRENTIN, EDMONDO;GORI, MARCO
2010-01-01
Abstract
Hybrid random fields are a recently proposed graphical model for pseudo-likelihood estimation in discrete domains. In this paper, we develop a continuous version of the model for nonparametric density estimation. To this aim, Nadaraya-Watson kernel estimators are used to model the local conditional densities within hybrid random fields. First, we introduce a heuristic algorithm for tuning the kernel bandwidhts in the conditional density estimators. Second, we propose a novel method for initializing the structure learning algorithm originally employed for hybrid random fields, which was meant instead for discrete variables. In order to test the accuracy of the proposed technique, we use a number of synthetic pattern classification benchmarks, generated from random distributions featuring nonlinear correlations between the variables. As compared to state-of-the-art nonparametric and semiparametric learning techniques for probabilistic graphical models, kernel-based hybrid random fields regularly outperform each considered alternative in terms of recognition accuracy, while preserving the scalability properties (with respect to the number of variables) that originally motivated their introduction.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/22182