MEAN DIMENSION OF RADIAL BASIS FUNCTIONS

被引:1
|
作者
Hoyt, Christopher [1 ]
Owen, Art B. [2 ]
机构
[1] Stanford Univ, Inst Computat & Math Engn, Stanford, CA 94305 USA
[2] Stanford Univ, Dept Stat, Stanford, CA 94305 USA
基金
美国国家科学基金会;
关键词
Jansen identity; Keister function; mesh-free approximation; multiquadrics; ALGORITHMS;
D O I
10.1137/23M1614833
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
We show that generalized multiquadric radial basis functions (RBFs) on R d have a mean dimension that is 1 + O (1 /d ) as d -+ oo with an explicit bound for the implied constant, under moment conditions on their inputs. Under weaker moment conditions the mean dimension still approaches 1. As a consequence, these RBFs become essentially additive as their dimension increases. Gaussian RBFs by contrast can attain any mean dimension between 1 and d . We also find that a test integrand due to Keister that has been influential in quasi -Monte Carlo theory has a mean dimension that oscillates between approximately 1 and approximately 2 as the nominal dimension d increases.
引用
收藏
页码:1191 / 1211
页数:21
相关论文
共 50 条
  • [1] Bayesian radial basis functions of variable dimension
    Holmes, CC
    Mallick, BK
    NEURAL COMPUTATION, 1998, 10 (05) : 1217 - 1233
  • [2] Radial Basis Functions
    Giesl, Peter
    CONSTRUCTION OF GLOBAL LYAPUNOV FUNCTIONS USING RADIAL BASIS FUNCTIONS, 2007, 1904 : 61 - 98
  • [3] Use of radial basis functions for estimating monthly mean daily solar radiation
    Mohandes, M
    Balghonaim, A
    Kassas, M
    Rehman, S
    Halawani, TO
    SOLAR ENERGY, 2000, 68 (02) : 161 - 168
  • [4] MEAN DIMENSION OF RIDGE FUNCTIONS
    Hoyt, Christopher R.
    Owen, Art B.
    SIAM JOURNAL ON NUMERICAL ANALYSIS, 2020, 58 (02) : 1195 - 1216
  • [5] Robustness of radial basis functions
    Eickhoff, R
    Rückert, U
    COMPUTATIONAL INTELLIGENCE AND BIOINSPIRED SYSTEMS, PROCEEDINGS, 2005, 3512 : 264 - 271
  • [6] Comparison of Radial Basis Functions
    Rozhenko, A., I
    NUMERICAL ANALYSIS AND APPLICATIONS, 2018, 11 (03) : 220 - 235
  • [7] Scaling of radial basis functions
    Larsson, Elisabeth
    Schaback, Robert
    IMA JOURNAL OF NUMERICAL ANALYSIS, 2024, 44 (02) : 1130 - 1152
  • [8] Deformable radial basis functions
    Huebner, Wolfgang
    Mallot, Hanspeter A.
    ARTIFICIAL NEURAL NETWORKS - ICANN 2007, PT 1, PROCEEDINGS, 2007, 4668 : 411 - +
  • [9] Applying radial basis functions
    Mulgrew, B
    IEEE SIGNAL PROCESSING MAGAZINE, 1996, 13 (02) : 50 - 65
  • [10] Robustness of radial basis functions
    Eickhoff, Ralf
    Rueckert, Ulrich
    NEUROCOMPUTING, 2007, 70 (16-18) : 2758 - 2767