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
  • [41] Scalable Nonparametric Low-Rank Kernel Learning Using Block Coordinate Descent
    Hu, En-Liang
    Kwok, James T.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (09) : 1927 - 1938
  • [42] Constant modulus algorithms via low-rank approximation
    Adler, Amir
    Wax, Mati
    SIGNAL PROCESSING, 2019, 160 : 263 - 270
  • [43] Linear low-rank approximation and nonlinear dimensionality reduction
    Zhenyue Zhang
    Hongyuan Zha
    Science in China Series A: Mathematics, 2004, 47 : 908 - 920
  • [44] Scaling Up Kernel SVM on Limited Resources: A Low-Rank Linearization Approach
    Lan, Liang
    Wang, Zhuang
    Zhe, Shandian
    Cheng, Wei
    Wang, Jun
    Zhang, Kai
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (02) : 369 - 378
  • [45] Low-rank approximation to entangled multipartite quantum systems
    Matthew M. Lin
    Moody T. Chu
    Quantum Information Processing, 21
  • [46] LOW-RANK APPROXIMATION OF MATRICES VIA A RANK-REVEALING FACTORIZATION WITH RANDOMIZATION
    Kaloorazi, Maboud Farzaneh
    Chen, Jie
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 5815 - 5819
  • [47] Sublinear Time Low-Rank Approximation of Positive Semidefinite Matrices
    Musco, Cameron
    Woodruff, David P.
    2017 IEEE 58TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS), 2017, : 672 - 683
  • [48] Sample-Optimal Low-Rank Approximation of Distance Matrices
    Indyk, Piotr
    Vakilian, Ali
    Wagner, Tal
    Woodruff, David P.
    CONFERENCE ON LEARNING THEORY, VOL 99, 2019, 99
  • [49] A gradient system approach for Hankel structured low-rank approximation
    Fazzi, Antonio
    Guglielmi, Nicola
    Markovsky, Ivan
    LINEAR ALGEBRA AND ITS APPLICATIONS, 2021, 623 : 236 - 257
  • [50] Modeling the Parameter Interactions in Ranking SVM with Low-Rank Approximation
    Xu, Jun
    Zeng, Wei
    Lan, Yanyan
    Guo, Jiafeng
    Cheng, Xueqi
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2019, 31 (06) : 1181 - 1193