Learning Graphical Model Parameters with Approximate Marginal Inference
Machine Learning
2014-07-04 v1 Computer Vision and Pattern Recognition
Abstract
Likelihood based-learning of graphical models faces challenges of computational-complexity and robustness to model mis-specification. This paper studies methods that fit parameters directly to maximize a measure of the accuracy of predicted marginals, taking into account both model and inference approximations at training time. Experiments on imaging problems suggest marginalization-based learning performs better than likelihood-based approximations on difficult problems where the model being fit is approximate in nature.
Cite
@article{arxiv.1301.3193,
title = {Learning Graphical Model Parameters with Approximate Marginal Inference},
author = {Justin Domke},
journal= {arXiv preprint arXiv:1301.3193},
year = {2014}
}
Comments
To Appear, IEEE Transactions on Pattern Analysis and Machine Intelligence