Presentation | 2015-06-23 A Bridge between Hedge and Exp3 Algorithms Atsuyoshi Nakamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Hedge is an online learning algorithm that draws an expert according to a probability distribution which depends on the performance of each expert so far. Hedge works for the {em full-information} setting, in which the rewards of all the experts are revealed. Exp3 is a Hedge-based algorithm modified so as to work for {em bandit} setting, in which only the reward of the selectedexpert is revealed. In this paper, we consider a new model with parameters ${gamma_i}$ that connect the two settings, and propose HExp3 algorithm that is an extension of both the two algorithms. We show upper and lower bounds of pseudo regret of HExp3. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | online learning / bandit / regret analysis |
Paper # | IBISML2015-13 |
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) | A Bridge between Hedge and Exp3 Algorithms |
Sub Title (in English) | |
Keyword(1) | online learning |
Keyword(2) | bandit |
Keyword(3) | regret analysis |
1st Author's Name | Atsuyoshi Nakamura |
1st Author's Affiliation | Hokkaido University(Hokkaido Univ.) |
Date | 2015-06-23 |
Paper # | IBISML2015-13 |
Volume (vol) | vol.115 |
Number (no) | IBISML-112 |
Page | pp.pp.81-86(IBISML), |
#Pages | 6 |
Date of Issue | 2015-06-16 (IBISML) |