| Presentation | 2015-06-23 Differential Privacy and Pseudo-Bayesian Posterior Kentaro Minami, Hiromi Arai, Issei Sato, Hiroshi Nakagawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We investigate relationship between differential privacy and pseudo-Bayesian posterior distributions. Recently, Wang, et al. proved that a parameter drawn from Bayesian posterior distribution automatically satisfies differential privacy. In this paper, we show that samples from pseudo-Bayesian posterior distributions satisfy $(varepsilon, delta)$-differential privacy. Our result can be applied to various problems in which loss functions are possibly unbounded. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | differential privacy / pseudo-Bayesian posterior / concentration of measure / PAC-Bayesian learning |
| Paper # | IBISML2015-7 |
| 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) | Differential Privacy and Pseudo-Bayesian Posterior |
| Sub Title (in English) | |
| Keyword(1) | differential privacy |
| Keyword(2) | pseudo-Bayesian posterior |
| Keyword(3) | concentration of measure |
| Keyword(4) | PAC-Bayesian learning |
| 1st Author's Name | Kentaro Minami |
| 1st Author's Affiliation | The University of Tokyo(The University of Tokyo) |
| 2nd Author's Name | Hiromi Arai |
| 2nd Author's Affiliation | The University of Tokyo(The University of Tokyo) |
| 3rd Author's Name | Issei Sato |
| 3rd Author's Affiliation | The University of Tokyo(The University of Tokyo) |
| 4th Author's Name | Hiroshi Nakagawa |
| 4th Author's Affiliation | The University of Tokyo(The University of Tokyo) |
| Date | 2015-06-23 |
| Paper # | IBISML2015-7 |
| Volume (vol) | vol.115 |
| Number (no) | IBISML-112 |
| Page | pp.pp.39-46(IBISML), |
| #Pages | 8 |
| Date of Issue | 2015-06-16 (IBISML) |