Asymptotic Bayesian Generalization Error When Training and Test Distributions Are Different
Abstract
In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standard machine learning techniques perform poorly. This paper focuses on revealing and improving the performance of Bayesian estimation when the training and test distributions are different. We formally analyze the asymptotic Bayesian generalization error and establish its upper bound under a very general setting. Our important finding is that lower order terms -- which can be ignored in the absence of the distribution change -- play an important role under the distribution change. We also propose a novel variant of stochastic complexity which can be used for choosing an appropriate model and hyper-parameters under a particular distribution change.
Cite
Text
Yamazaki et al. "Asymptotic Bayesian Generalization Error When Training and Test Distributions Are Different." International Conference on Machine Learning, 2007. doi:10.1145/1273496.1273632Markdown
[Yamazaki et al. "Asymptotic Bayesian Generalization Error When Training and Test Distributions Are Different." International Conference on Machine Learning, 2007.](https://mlanthology.org/icml/2007/yamazaki2007icml-asymptotic/) doi:10.1145/1273496.1273632BibTeX
@inproceedings{yamazaki2007icml-asymptotic,
title = {{Asymptotic Bayesian Generalization Error When Training and Test Distributions Are Different}},
author = {Yamazaki, Keisuke and Kawanabe, Motoaki and Watanabe, Sumio and Sugiyama, Masashi and Müller, Klaus-Robert},
booktitle = {International Conference on Machine Learning},
year = {2007},
pages = {1079-1086},
doi = {10.1145/1273496.1273632},
url = {https://mlanthology.org/icml/2007/yamazaki2007icml-asymptotic/}
}