A Least-squares Approach to Direct Importance Estimation

@article{Kanamori2009ALA,
  title={A Least-squares Approach to Direct Importance Estimation},
  author={Takafumi Kanamori and Shohei Hido and Masashi Sugiyama},
  journal={Journal of Machine Learning Research},
  year={2009},
  volume={10},
  pages={1391-1445}
}
We address the problem of estimating the ratio of two probabi lity density functions, which is often referred to as theimportance. The importance values can be used for various succeeding ta sks such ascovariate shift adaptationor outlier detection. In this paper, we propose a new importance estimation method that has a closed-form solution; the leav e-one-out cross-validation score can also be computed analytically. Therefore, the proposed method i s computationally highly efficient and simple… CONTINUE READING
Highly Influential
This paper has highly influenced 22 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 336 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 176 extracted citations

336 Citations

0204060'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 336 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-3 of 3 references

An algorithm for the solution of the parametric quadratic programmin

  • Athena Scientific, MA Belmont
  • 2003

Similar Papers

Loading similar papers…