Presentation | 2015-06-23 Efficient sparse learning for combinatorial model by using safe screening approach Kazuya Nakagawa, Shinya Suzumura, Masayuki Karasuyama, Ichiro Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In a variety of machine learning tasks, it has been desired to incorporate high-order interaction effects of multiple covariates. However, for recent applications with a large number covariates, it is highly challenging to identify important high-order interaction features since the number of possible candidates would be extremely large. In this paper, we propose an efficient algorithm for LASSO-based sparse learning of such high-order interaction models. The basic strategy is to use a recently introduced safe feature screening technique by which a subset of non-active features can be identified and they can be screened-out prior to LASSO training. However, applying safe feature screening to each of the extremely large number of high-order interaction features would be computationally infeasible. Our key idea for solving this computational issue is to exploit the underlying tree structure among high-order interaction features. Specifically, we introduce a set of pruning conditions of the tree such that, if one of the conditions is satised in a certain node, then all the high-order interaction features corresponding to its descendant nodes can be guaranteed to be non-active at the optimal solution, and they can be screened-out prior to LASSO training. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | high-order interaction model / LASSO / sparse learning / safe-screening |
Paper # | IBISML2015-10 |
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) | Efficient sparse learning for combinatorial model by using safe screening approach |
Sub Title (in English) | |
Keyword(1) | high-order interaction model |
Keyword(2) | LASSO |
Keyword(3) | sparse learning |
Keyword(4) | safe-screening |
1st Author's Name | Kazuya Nakagawa |
1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
2nd Author's Name | Shinya Suzumura |
2nd Author's Affiliation | Nagoya Institute of Technology(NIT) |
3rd Author's Name | Masayuki Karasuyama |
3rd Author's Affiliation | Nagoya Institute of Technology(NIT) |
4th Author's Name | Ichiro Takeuchi |
4th Author's Affiliation | Nagoya Institute of Technology(NIT) |
Date | 2015-06-23 |
Paper # | IBISML2015-10 |
Volume (vol) | vol.115 |
Number (no) | IBISML-112 |
Page | pp.pp.63-68(IBISML), |
#Pages | 6 |
Date of Issue | 2015-06-16 (IBISML) |