Dimensionality reduction for density ratio estimation in high-dimensional spaces

作者：Sugiyama Masashi^*; Kawanabe Motoaki; Chui Pui Ling

来源：Neural Networks, 2010, 23(1): 44-59.

DOI：10.1016/j.neunet.2009.07.007

• Density ratio estimation
• Dimensionality reduction
• Local Fisher discriminant analysis
• Unconstained least-squares importance fitting

The ratio of two prohability density functions is becoming a quantity of interest of these days in the machine learning and data mining communities since it can be used far various data processing tasks such as non-stationarity adaptation, outlier detection, and feature selection Recently. several methods have been developed for directly estimating the de nsity ratio without going through density estimation and were shown to work well in various practical problems. However, these methods still perform rather poorly when the dimensionality of the data domain is high. In this paper, we propose to incorporate a dimensionality reduction scheme into a density-ratio estimation procedure and experimentally show that the estimation accuracy in high-dimensional cases can be improved.

• 出版日期2010-1