Abstract
AbstractWe describe a natural coisometry from the Hilbert space of all Hilbert-Schmidt operators on a separable reproducing kernel Hilbert space $$\hbox { (RKHS)}\, \mathcal {H}$$
(RKHS)
H
and onto the RKHS $$\mathcal {G}$$
G
associated with the squared-modulus of the reproducing kernel of $$\mathcal {H}$$
H
. Through this coisometry, trace-class integral operators defined by general measures and the reproducing kernel of $$\mathcal {H}$$
H
are isometrically represented as potentials in $$\mathcal {G}$$
G
, and the quadrature approximation of these operators is equivalent to the approximation of integral functionals on $$\mathcal {G}$$
G
. 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.
Publisher
Springer Science and Business Media LLC
Reference28 articles.
1. Aronszajn, N.: Theory of reproducing kernels. Trans. Am. Math. Soc. 68(3), 337–404 (1950)
2. Bach, F.: On the equivalence between kernel quadrature rules and random feature expansions. J. Mach. Learn. Res. 18(1), 714–751 (2017)
3. Conway, J.B.: A Course in Functional Analysis, vol. 96. Springer (2019)
4. Cucker, F., Smale, S.: On the mathematical foundations of learning. Bull. Am. Math. Soc. 39, 1–49 (2002)
5. Cucker, F., Xuan Zhou, D.: Learning Theory: an Approximation Theory Viewpoint. Cambridge University Press (2007)