Randomized sketches for kernel CCA
Randomized sketches for kernel CCA
复制标题
内核 CCA 的随机草图
DOI:
10.1016/j.neunet.2020.04.006
复制
发表时间:
2020-04
期刊:
影响因子:
7.8
通讯作者:
Wenqi Lu
中科院分区:
文献类型:
--
作者:
Heng Lian;Fode Zhang;Wenqi Lu
Kernel canonical correlation analysis (KCCA) is a popular tool as a nonlinear extension of canonical correlation analysis. Consistency and optimal convergence rate have been established in the literature. However, the time complexity of KCCA scales as O (n 3) and is thus prohibitive when n is large. We propose an m-dimensional randomized sketches approach for KCCA with m<< n, based on the recent work on randomized sketches for kernel ridge regression (KRR). Technically we establish our theoretical results relying on an interesting connection between KCCA and KRR by utilizing a novel “duality tracking” device that alternates between the infinite-dimensional operator-theory-based view of KCCA and the finite-dimensional kernel-matrix-based view.
登录
查看更多内容
DOI:
10.1016/j.jmva.2016.05.008
发表时间:
2016-09
期刊:
J. Multivar. Anal.
影响因子:
--
作者:
Zengyan Fan;H. Lian
通讯作者:
Zengyan Fan;H. Lian
影响因子:
1
作者:
Brad Ballinger;Nadia M. Benbernou;Prosenjit Bose;Mirela Damian;E. Demaine;V. Dujmovic;Robin Y. Flatland;Ferran Hurtado;J. Iacono;A. Lubiw;Pat Morin;Vera Sacristán Adinolfi;D. Souvaine;Ryuhei Uehara
通讯作者:
Brad Ballinger;Nadia M. Benbernou;Prosenjit Bose;Mirela Damian;E. Demaine;V. Dujmovic;Robin Y. Flatland;Ferran Hurtado;J. Iacono;A. Lubiw;Pat Morin;Vera Sacristán Adinolfi;D. Souvaine;Ryuhei Uehara
影响因子:
4.5
作者:
Zhao T;Cheng G;Liu H
通讯作者:
Liu H
DOI:
10.1214/16-aos1472
发表时间:
2015-01
期刊:
ArXiv
影响因子:
--
作者:
Yun Yang;Mert Pilanci;M. Wainwright
通讯作者:
Yun Yang;Mert Pilanci;M. Wainwright
DOI:
10.5555/2789272.2831141
发表时间:
2013-06
期刊:
ArXiv
影响因子:
--
作者:
Ping Ma;Michael W. Mahoney;Bin Yu
通讯作者:
Ping Ma;Michael W. Mahoney;Bin Yu