Learning CRFs with Hierarchical Features : An Application to Go

We investigate the task of learning grid-based CRFs with hierarchical features motivated by the task of territory prediction in Go. We first analyze various independent and gridbased CRF classification models and state-ofthe-art training/inference algorithms to determine which offers the best performance across a variety of metrics. Faced with the performance drawbacks of independent models and the computational drawbacks of intractable CRF models, we introduce the BMA-Tree algorithm that uses Bayesian model averaging of tree-structured predictors to exploit hierarchical feature structure. Our results demonstrate that BMA-Tree is superior to other independent classifiers and provides a computationally efficient alternative to intractable grid-based CRF models when training is too slow or approximate inference is inadequate for the task at hand.