ICML 2016poster593 citations
A Kernelized Stein Discrepancy for Goodness-of-fit Tests
Qiang Liu, Jason Lee, Michael Jordan
Abstract
We derive a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein’s identity and the reproducing kernel Hilbert space theory. We apply our result to test how well a probabilistic model fits a set of observations, and derive a new class of powerful goodness-of-fit tests that are widely applicable for complex and high dimensional distributions, even for those with computationally intractable normalization constants. Both theoretical and empirical properties of our methods are studied thoroughly.
BibTeX
@InProceedings{pmlr-v48-liub16,
title = {A Kernelized Stein Discrepancy for Goodness-of-fit Tests},
author = {Liu, Qiang and Lee, Jason and Jordan, Michael},
booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
pages = {276--284},
year = {2016},
editor = {Balcan, Maria Florina and Weinberger, Kilian Q.},
volume = {48},
series = {Proceedings of Machine Learning Research},
address = {New York, New York, USA},
month = {20--22 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v48/liub16.pdf},
url = {https://proceedings.mlr.press/v48/liub16.html},
abstract = {We derive a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein’s identity and the reproducing kernel Hilbert space theory. We apply our result to test how well a probabilistic model fits a set of observations, and derive a new class of powerful goodness-of-fit tests that are widely applicable for complex and high dimensional distributions, even for those with computationally intractable normalization constants. Both theoretical and empirical properties of our methods are studied thoroughly.}
}