Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gruber, Lukas, Holzleitner, Markus, Lehner, Johannes, Hochreiter, Sepp, Zellinger, Werner
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913374950916096
author Gruber, Lukas
Holzleitner, Markus
Lehner, Johannes
Hochreiter, Sepp
Zellinger, Werner
author_facet Gruber, Lukas
Holzleitner, Markus
Lehner, Johannes
Hochreiter, Sepp
Zellinger, Werner
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13891
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
Gruber, Lukas
Holzleitner, Markus
Lehner, Johannes
Hochreiter, Sepp
Zellinger, Werner
Machine Learning
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.
title Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
topic Machine Learning
url https://arxiv.org/abs/2402.13891