Kernel embedding of measures and low-rank approximation of integral operators

被引:0
|
作者
Gauthier, Bertrand [1 ]
机构
[1] Cardiff Univ, Sch Math, Abacws,Senghennydd Rd, Cardiff CF24 4AG, Wales
关键词
Reproducing kernel Hilbert spaces; Integral operators; Low-rank approximation; Kernel embedding of measures; Differentiable relaxation; NYSTROM METHOD; METRICS;
D O I
10.1007/s11117-024-01041-8
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
We describe a natural coisometry from the Hilbert space of all Hilbert-Schmidt operators on a separable reproducing kernel Hilbert space (RKHS) H \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\hbox { (RKHS)}\, \mathcal {H}$$\end{document} and onto the RKHS G \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {G}$$\end{document} associated with the squared-modulus of the reproducing kernel of H \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {H}$$\end{document} . Through this coisometry, trace-class integral operators defined by general measures and the reproducing kernel of H \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {H}$$\end{document} are isometrically represented as potentials in G \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {G}$$\end{document} , and the quadrature approximation of these operators is equivalent to the approximation of integral functionals on G \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {G}$$\end{document} . We then discuss the extent to which the approximation of potentials in RKHSs with squared-modulus kernels can be regarded as a differentiable surrogate for the characterisation of low-rank approximation of integral operators.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Is Input Sparsity Time Possible for Kernel Low-Rank Approximation?
    Musco, Cameron
    Woodruff, David P.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [2] Error Bounds for Low-Rank Approximations of the First Exponential Integral Kernel
    Nunes, A. L.
    Vasconcelos, P. B.
    Ahues, M.
    NUMERICAL FUNCTIONAL ANALYSIS AND OPTIMIZATION, 2013, 34 (01) : 74 - 93
  • [3] Kernel Wiener filtering model with low-rank approximation for image denoising
    Zhang, Yongqin
    Xiao, Jinsheng
    Peng, Jinye
    Ding, Yu
    Liu, Jiaying
    Guo, Zongming
    Zong, Xiaopeng
    INFORMATION SCIENCES, 2018, 462 : 402 - 416
  • [4] Dynamical low-rank approximation
    Koch, Othmar
    Lubich, Christian
    SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2007, 29 (02) : 434 - 454
  • [5] Joint Embedding Learning and Low-Rank Approximation: A Framework for Incomplete Multiview Learning
    Tao, Hong
    Hou, Chenping
    Yi, Dongyun
    Zhu, Jubo
    Hu, Dewen
    IEEE TRANSACTIONS ON CYBERNETICS, 2021, 51 (03) : 1690 - 1703
  • [6] Multiscale Decomposition in Low-Rank Approximation
    Abdolali, Maryam
    Rahmati, Mohammad
    IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (07) : 1015 - 1019
  • [7] RANDOMIZED LOW-RANK APPROXIMATION FOR SYMMETRIC INDEFINITE MATRICES
    Nakatsukasa, Yuji
    Park, Taejun
    SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2023, 44 (03) : 1370 - 1392
  • [8] Speech enhancement method based on low-rank approximation in a reproducing kernel Hilbert space
    Zhao, Yanping
    Qiu, Robert Caiming
    Zhao, Xiaohui
    Wang, Bo
    APPLIED ACOUSTICS, 2016, 112 : 79 - 83
  • [9] KERNEL OPTIMIZATION FOR LOW-RANK MULTIFIDELITY ALGORITHMS
    Razi, Mani
    Kirby, Robert M.
    Narayan, Akil
    INTERNATIONAL JOURNAL FOR UNCERTAINTY QUANTIFICATION, 2021, 11 (01) : 31 - 54
  • [10] Sparse semi-supervised learning on low-rank kernel
    Zhang, Kai
    Wang, Qiaojun
    Lan, Liang
    Sun, Yu
    Marsic, Ivan
    NEUROCOMPUTING, 2014, 129 : 265 - 272