I'm a CS student and I'm trying to learn RKHS theory to understand the passages made in this paper . Among the bibliography I'm using there are "On the mathematical fundamentals of learning" and "Learning with Kernels". I think I've got a good grasp of the relevant theory, but there's still something that bugs me.

As far as I understood a RKHS is a Hilbert space $H\subseteq \mathbb{C}^X$, where $X$ is a generic set of objects, with inner product $\langle f,g\rangle=\int_X\int_X \alpha(x')\beta(x)k(x,x')dxdx'$ with $\alpha,\beta \in \mathbb{C}^X$, $f=\int_X\alpha(x')k(x,x')dx'$ and $g=\int_X\beta(x')k(x,x')dx'$ such that $H=\overline{\mathrm{span}\{k_x|x\in X\}}$ and $\langle f,k_x\rangle=f(x)$ where $k_x=k(.,x)\;\forall x\in X$ and $k$ is the (Mercer) kernel for $H$. Let's call this "continuos-whole" definition.

However, given $D=\{x_1,x_2,...x_n\}\subset X$ a subspace $H_D\subset H$ could be defined by restricting the definition above to $H_D=\overline{\mathrm{span}\{k_{x_i}|x_i\in D\}}=\{f\in \mathbb{C}^X|f=\overset{i=s}{\underset{i=1}{\sum}} \alpha_ik(x,x_i)\quad \alpha_i\in \mathbb{C} \;, r\in \mathbb{N}\}$ and thus define $\langle f,g\rangle_{H_D}=\overset{i=s}{\sum_{i=1}}\overset{j=s}{\sum_{j=1}}\alpha_i\beta_jk(x_i,x_j)$. Let this be the "discrete-finite" definition

Assuming this is correct, the references tend to define $H$ as both being spanned by $\{k_x|x \in X\}$ and having inner product $\langle .,.\rangle_{H_D}$, and that would be possible if and only if $\overline{\mathrm{span}\{k_x|x\in X\}}=\overline{\mathrm{span}\{k_{x_i}|x_i\in D\}}$ which seems bogus to me.

Then, regarding the article, there's a passage of which I'm unsure. Let $H$ be a RKHS, i.e. a Hilbert space s.t. every point-evaluation functional is bounded, which would entail a "whole-continuous" definition. Then $H$ can be orthogonal decomposed in $H=H_D\oplus H_D^\bot$ where $H_D^\bot \bot H_D \rightarrow \langle f,g\rangle=0 \forall f\in H_D \;\wedge\; g\in H_D^\bot$. The paper says that $H_D^\bot=\{g|g(x_i)=0\forall x_i\in D\}$. Starting from the definition of orthogonality, I carried out the following proof: $\forall f \in H_D \;\wedge\; g \in H_D^\top$ $\langle f,g \rangle=\int_X\int_X \alpha(x')\beta(x)k(x,x')dxdx'=\int_X \beta(x)f(x)dx$ $=\sum_{i \in 1..s}\alpha_i\int_X \beta(x)k(x,x_i)dx=\sum_{i \in 1..s} \alpha_i g(x_i)=0 \forall \alpha_i \in \mathbb{C}\rightarrow g(x_i)=0 \forall i\in 1..s$, for which I applied the reproducing property and the definiton of $g$ in this order. is this correct?

EDIT:I know the definition via the Riesz theorem, however I'm referring to the definiton I found in "Learning with kernels" (pg. 36):

"Definition 2.9 (Reproducing Kernel Hilbert Space) Let $X$ be a nonempty set and by $H$ a Hilbert space of functions $f :X\rightarrow\mathbb{R}$ . Then $H$ is called a reproducing kernel Hilbert space endowed with the dot product $\langle .,. \rangle$ (and the norm $||f|| : \sqrt \langle f ,f\rangle $ ) if there exists afunction $k :X\times X \rightarrow \mathbb{R}$ with the following properties:

  1. $k$ has the reproducing property $\langle f, k(x,. )\rangle= f(x)$ for all $f\in H$ ;

  2. $k$ spans $H$ , i.e. $H=\overline{\mathrm{span}\{k(x,.)| x \in X\}}$ where $\overline{X}$ denotes the completion of the set $X$"

, and, to my understanding, it is based on the theorems characterising RKHS on Mercer kernels (see pg. 35 of "On the mathematical foundations of Learning"). The approach they take, as far as I've understood, is inside-out: they start from a Lp space $H=\overline{\mathrm{span}\{k(x,.)| x \in X\}}$ with $k$ being a (Mercer) kernel, for which define a suitable inner product to get a Hilbert space that is also a RKHS. They defined a Mercer kernel to be a function $X^2\rightarrow \mathbb{R}$ that gives rise to a definite positive Gram matrix $K_{ij}=k(x_i,x_j)$ for every $D=\{x_1,x_2..x_n\}\subset X$.

  • 2
    $\begingroup$ A remark concerning your "definitions": Definition: a RKHS over $\mathbb{C}$ is a Hilbert space $H$ that as a vector space is a subspace of the vector space $\mathbb{C}^X$ and that has the property, that for every $x\in X$ the evaluation functional $H\rightarrow\mathbb{C},\; h\mapsto h(x)$ is continous. In particular you cannot define the scalar product: it is given, $H$ is a Hilbert space. Similarly the kernel $k$ is determined by the structure of $H$ via Riesz representation. Against that background I do not understand the two definitions you are talking about. $\endgroup$
    – Hagen
    Commented Jul 11, 2011 at 14:21
  • $\begingroup$ The first link no longer works, but from Wayback Machine one can see that is a link to the paper Beyond the point cloud: from transductive to semi-supervised learning. $\endgroup$ Commented Mar 4, 2023 at 12:21

1 Answer 1


To answer your second question:

$H_D = \operatorname{span}(k_x : x \in D) $ is a finite dimensional (and hence closed) subspace of $H$. A function $f \in H$ is orthogonal to each $k_x, x \in D$ precisely when $\langle f , k_x \rangle = f(x) = 0$. In other words, $H_D^\perp = ( f \in H : f(x_i) = 0, x_i \in D)$ and of course $H = H_D \oplus H_D^\perp$.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.