| Presentation | 2020-03-05 Bayesian learning curve for the case when the optimal distribution is not unique Shuya Nagayasu, Sumio Watanabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Bayesian inference is a widely used statistical method. Asymptotic behaviors of generalization loss and free energy in Bayesian inference are revealed in singular models that do not have unique optimal parameter which makes generalization loss minimum with the method using algebric geometry, but it has not been revealed when there are multiple optimal probability distributions. In the present paper, we derive asymptotic behavior of generalization loss and free energy in case optimal probability distribution is not unique, and show that it is different from the learning curve of conventional learning theory. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | statistical estimation / Bayesian inference / generalization loss / free energy / singular model |
| Paper # | NC2019-94 |
| Date of Issue | 2020-02-26 (NC) |
| Conference Information | |
| Committee | NC / MBE |
|---|---|
| Conference Date | 2020/3/4(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | University of Electro Communications |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Neuro Computing, Medical Engineering, etc. |
| Chair | Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.) |
| Vice Chair | Kazuyuki Samejima(Tamagawa Univ) / Takashi Watanabe(Tohoku Univ.) |
| Secretary | Kazuyuki Samejima(NAIST) / Takashi Watanabe(NTT) |
| Assistant | Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Yasuyuki Suzuki(Osaka Univ.) / Akihiro Karashima(Tohoku Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Bayesian learning curve for the case when the optimal distribution is not unique |
| Sub Title (in English) | |
| Keyword(1) | statistical estimation |
| Keyword(2) | Bayesian inference |
| Keyword(3) | generalization loss |
| Keyword(4) | free energy |
| Keyword(5) | singular model |
| 1st Author's Name | Shuya Nagayasu |
| 1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
| 2nd Author's Name | Sumio Watanabe |
| 2nd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
| Date | 2020-03-05 |
| Paper # | NC2019-94 |
| Volume (vol) | vol.119 |
| Number (no) | NC-453 |
| Page | pp.pp.107-112(NC), |
| #Pages | 6 |
| Date of Issue | 2020-02-26 (NC) |