| Presentation | 2017-06-20 On Contributions of Principal Eigenfunctions of Covariance Operator of Kernel Feature Vectors to Relevant Information in Nonlinear Regression Masahiro Yukawa, Klaus-Robert Muller, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We study, through simple non-asymptotic arguments, the contributions of eigenfunctions of the covariance operator of kernel feature vectors to the relevant information in nonlinear regression under the explicit centering. Although the contribution of an eigenfunction contains a term which decays as the same rate as the eigenvalues (as shown by Braun, Buhmann, and Muller in 2008), it also contains a constant term which comes from the centering operation. Our simple derivations lead to an exact analytic form of the contribution containing no truncation errors. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | nonlinear regressionkernel PCAreproducing kernel Hilbert space |
| Paper # | CAS2017-16,VLD2017-19,SIP2017-40,MSS2017-16 |
| Date of Issue | 2017-06-12 (CAS, VLD, SIP, MSS) |
| Conference Information | |
| Committee | SIP / CAS / MSS / VLD |
|---|---|
| Conference Date | 2017/6/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Niigata University, Ikarashi Campus |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Masahiro Okuda(Univ. of Kitakyushu) / Mitsuru Hiraki(Renesas) / Morikazu Nakamura(Univ. of Ryukyus) / Hiroyuki Ochi(Ritsumeikan Univ.) |
| Vice Chair | Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) / Hideaki Okazaki(Shonan Inst. of Tech.) / Shigemasa Takai(Osaka Univ.) / Noriyuki Minegishi(Mitsubishi Electric) |
| Secretary | Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) / Hideaki Okazaki(Renesas) / Shigemasa Takai(Shonan Inst. of Tech.) / Noriyuki Minegishi(Toshiba) |
| Assistant | Masayoshi Nakamoto(Hiroshima Univ.ひろ) / Yohei Nakamura(Hitachi) / Hideki Kinjo(Okinawa Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Signal Processing / Technical Committee on Circuits and Systems / Technical Committee on Mathematical Systems Science and its applications / Technical Committee on VLSI Design Technologies |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On Contributions of Principal Eigenfunctions of Covariance Operator of Kernel Feature Vectors to Relevant Information in Nonlinear Regression |
| Sub Title (in English) | |
| Keyword(1) | nonlinear regressionkernel PCAreproducing kernel Hilbert space |
| 1st Author's Name | Masahiro Yukawa |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Klaus-Robert Muller |
| 2nd Author's Affiliation | Technical University of Berlin(TU BerlinTechnical U) |
| Date | 2017-06-20 |
| Paper # | CAS2017-16,VLD2017-19,SIP2017-40,MSS2017-16 |
| Volume (vol) | vol.117 |
| Number (no) | CAS-96,VLD-97,SIP-98,MSS-99 |
| Page | pp.pp.81-85(CAS), pp.81-85(VLD), pp.81-85(SIP), pp.81-85(MSS), |
| #Pages | 5 |
| Date of Issue | 2017-06-12 (CAS, VLD, SIP, MSS) |