Presentation | 2015-06-23 Risk Bound of Lasso Based on MDL Theory Masanori Kawakita, Yushin Toyokihara, Jun'ichi Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We derive a risk bound of lasso in random design linear regression. Pastworks of MDL principle revealed that penalized maximum likelihood methodscan be interpreted as a two stage coding procedure and have a redundancyrisk bound. Barron et. al. derived a risk bound of lasso in fixed designlinear regression by extending those past works. To assess thegeneralization error, however, we need to consider the random designsetting, which is much more difficult. We give a risk bound (and aregret bound) of lasso in random design cases under normality ofcovariates as a first step. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | lasso / risk bound / MDL principle / two stage coding |
Paper # | IBISML2015-16 |
Date of Issue | 2015-06-16 (IBISML) |
Conference Information | |
Committee | NC / IPSJ-BIO / IBISML / IPSJ-MPS |
---|---|
Conference Date | 2015/6/23(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Institute of Science and Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Machine Learning Approach to Biodata Mining, and General |
Chair | Toshimichi Saito(Hosei Univ.) / Masakazu Sekijima(東工大) / Takashi Washio(Osaka Univ.) / Hayaru Shouno(電通大) |
Vice Chair | Shigeo Sato(Tohoku Univ.) / / Kenji Fukumizu(ISM) / Masashi Sugiyama(Tokyo Inst. of Tech.) |
Secretary | Shigeo Sato(Kyushu Inst. of Tech.) / (Kyoto Sangyo Univ.) / Kenji Fukumizu(京大) / Masashi Sugiyama(お茶の水女子大) / (OIST) |
Assistant | Hiroyuki Kanbara(Tokyo Inst. of Tech.) / Hisanao Akima(Tohoku Univ.) / / Koji Tsuda(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Special Interest Group on Bioinformatics and Genomics / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Risk Bound of Lasso Based on MDL Theory |
Sub Title (in English) | |
Keyword(1) | lasso |
Keyword(2) | risk bound |
Keyword(3) | MDL principle |
Keyword(4) | two stage coding |
1st Author's Name | Masanori Kawakita |
1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
2nd Author's Name | Yushin Toyokihara |
2nd Author's Affiliation | Kyushu University(Kyushu Univ.) |
3rd Author's Name | Jun'ichi Takeuchi |
3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
Date | 2015-06-23 |
Paper # | IBISML2015-16 |
Volume (vol) | vol.115 |
Number (no) | IBISML-112 |
Page | pp.pp.101-107(IBISML), |
#Pages | 7 |
Date of Issue | 2015-06-16 (IBISML) |