Direct Density-Ratio Estimation with Dimensionality Reduction via Hetero-Distributional Subspace Analysis

Authors

  • Makoto Yamada Tokyo Institute of Technology
  • Masashi Sugiyama Tokyo Institute of Technology

Abstract

Methods for estimating the ratio of two probability density functions have been actively explored recently since they can be used for various data processing tasks such as non-stationarity adaptation, outlier detection, feature selection, and conditional probability estimation. In this paper, we propose a new density-ratio estimator which incorporates dimensionality reduction into the density-ratio estimation procedure. Through experiments, the proposed method is shown to compare favorably with existing density-ratio estimators in terms of both accuracy and computational costs.

Downloads

Published

2011-08-04

How to Cite

Yamada, M., & Sugiyama, M. (2011). Direct Density-Ratio Estimation with Dimensionality Reduction via Hetero-Distributional Subspace Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 25(1), 549-554. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/7905

Issue

Section

AAAI Technical Track: Machine Learning