Presentation | 2013-12-21 Conditional Density Estimation with Feature Selection Motoki SHIGA, Masashi SUGIYAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | On identification of the statistical dependency between inputs and outputs, an conditional density estimation is essential. The least-squares conditional density estimator (LS-CDE) proposed by Sugiyama et al. is more efficient and more applicable for more complex structures than regression models, which estimate the conditional mean of outputs. However, LS-CDE still suffers from large estimation error when many irrelevant features exist in inputs. In this paper, we propose extending LS-CDE to allow simultaneous feature selection during conditional density estimation. We evaluated our proposed method by numerical experiments. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Conditional density estimation / Feature selection / Sparse structured norm |
Paper # | NC2013-56 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2013/12/14(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Conditional Density Estimation with Feature Selection |
Sub Title (in English) | |
Keyword(1) | Conditional density estimation |
Keyword(2) | Feature selection |
Keyword(3) | Sparse structured norm |
1st Author's Name | Motoki SHIGA |
1st Author's Affiliation | Informatics Course, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University() |
2nd Author's Name | Masashi SUGIYAMA |
2nd Author's Affiliation | Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology |
Date | 2013-12-21 |
Paper # | NC2013-56 |
Volume (vol) | vol.113 |
Number (no) | 374 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |