NeurIPS 2018poster0 citations
PAC-Bayes Tree: weighted subtrees with guarantees
Abstract
We present a weighted-majority classification approach over subtrees of a fixed tree, which provably achieves excess-risk of the same order as the best tree-pruning. Furthermore, the computational efficiency of pruning is maintained at both training and testing time despite having to aggregate over an exponential number of subtrees. We believe this is the first subtree aggregation approach with such guarantees.
BibTeX
@inproceedings{NEURIPS2018_1819020b,
author = {Nguyen, Tin D and Kpotufe, Samory},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {PAC-Bayes Tree: weighted subtrees with guarantees},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/1819020b02e926785cf3be594d957696-Paper.pdf},
volume = {31},
year = {2018}
}