An Error Analysis of Deep Density-Ratio Estimation with Bregman Divergence
Lists
Only you see this
Abstract
We establish non-asymptotic error bounds for a nonparametric density-ratio estimator using deep neural networks with the Bregman divergence. We also show that the deep density-ratio estimator can mitigate the curse of dimensionality when the data is supported on an approximate low-dimensional manifold. Our error bounds are optimal in the minimax sense and the pre-factors in our error bounds depend on the dimensionality of the data polynomially. We apply our results to investigate the convergence properties of the telescoping density-ratio estimator (Rhodes et al., 2020) and provide sufficient conditions under which it has a smaller upper error bound than a single-ratio estimator.
BibTeX
@inproceedings{zheng2022error,
author = {Siming Zheng and GUOHAO SHEN and Yuling Jiao and Yuanyuan Lin and Jian Huang},
title = {{An Error Analysis of Deep Density-Ratio Estimation with Bregman Divergence}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2022},
url = {https://openreview.net/forum?id=dfOBSd3tF9p},
}Loading related content...