| Presentation | 2022-03-08 Real log canonical threshold of reduced rank regression when inputs are on a low dimensional hyperplane Joe Hirose, Sumio Watanabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A reduced rank regression is a statistical model which estimates a linear regression function from in- puts to outputs with a restricted rank. Its generalization performance in Bayesian inference is given by a real log canonical threshold (RLCT), and its concrete values were clarified by an algebro-geometric method. However, such results needed a condition that the distribution of inputs are not degenerate. In this paper, we prove that RLCT of a reduced rank regression when the distribution of inputs is on a low dimensional hyperplane. It is also reported that the theoretical results coincided with a numerical experiment. Our result shows that the generalization loss does not increase even if the inputs are redundant for essential distribution. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Reduced Rank Regression / Real Log Canonical Threshold / Generalization Error |
| Paper # | IBISML2021-32 |
| Date of Issue | 2022-03-01 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2022/3/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Machine Learning, etc. |
| Chair | Ichiro Takeuchi(Nagoya Inst. of Tech.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(Univ. of Tokyo) |
| Assistant | Tomoharu Iwata(NTT) / Atsuyoshi Nakamura(Hokkaido Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Real log canonical threshold of reduced rank regression when inputs are on a low dimensional hyperplane |
| Sub Title (in English) | |
| Keyword(1) | Reduced Rank Regression |
| Keyword(2) | Real Log Canonical Threshold |
| Keyword(3) | Generalization Error |
| 1st Author's Name | Joe Hirose |
| 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 | 2022-03-08 |
| Paper # | IBISML2021-32 |
| Volume (vol) | vol.121 |
| Number (no) | IBISML-419 |
| Page | pp.pp.15-18(IBISML), |
| #Pages | 4 |
| Date of Issue | 2022-03-01 (IBISML) |