Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
Abstract
Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kernel methods for density ratio estimation suffers from error saturation, which prevents algorithms from achieving fast error convergence rates on highly regular learning problems. To resolve saturation, we introduce iterated regularization in density ratio estimation to achieve fast error rates. Our methods outperform its non-iteratively regularized versions on benchmarks for density ratio estimation as well as on large-scale evaluations for importance-weighted ensembling of deep unsupervised domain adaptation models.
Cite
Text
Gruber et al. "Overcoming Saturation in Density Ratio Estimation by Iterated Regularization." International Conference on Machine Learning, 2024.Markdown
[Gruber et al. "Overcoming Saturation in Density Ratio Estimation by Iterated Regularization." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/gruber2024icml-overcoming/)BibTeX
@inproceedings{gruber2024icml-overcoming,
title = {{Overcoming Saturation in Density Ratio Estimation by Iterated Regularization}},
author = {Gruber, Lukas and Holzleitner, Markus and Lehner, Johannes and Hochreiter, Sepp and Zellinger, Werner},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {16502-16529},
volume = {235},
url = {https://mlanthology.org/icml/2024/gruber2024icml-overcoming/}
}