Theoretical Analysis of Density-Ratio Estimation

Masashi Sugiyama, Taiji Suzuki, Takafumi KanamoriCambridge 2012 · DOI · OpenAlex

Abstract

In Chapter 13, we analyze the asymptotic properties of density-ratio estimation. We first establish the consistency and asymptotic normality of the KLIEP method (see Chapter 5) in Section 13.1, and we elucidate the asymptotic learning curve of the LSIF method (see Chapter 6) in Section 13.2. Then, in Section 13.3, we explain that the logistic regression method (see Chapter 4) achieves the minimum asymptotic variance when the parametric model is specified correctly. Finally, in Section 13.4, we compare theoretically the performance of density-ratio estimation methods, showing that separate density estimation (see Chapter 2) is favorable if correct density models are available, and direct density-ratio estimation is favorable otherwise.
BibTeX
@inproceedings{sugiyama2012theoretical,
  author = {Masashi Sugiyama and Taiji Suzuki and Takafumi Kanamori},
  title = {{Theoretical Analysis of Density-Ratio Estimation}},
  booktitle = {Cambridge},
  year = {2012},
  doi = {10.1017/cbo9781139035613.017},
}

Loading related content...

Figure