Behavior of a functional in learning theory (Q934356): Difference between revisions
From MaRDI portal
Set OpenAlex properties. |
ReferenceBot (talk | contribs) Changed an Item |
||
Property / cites work | |||
Property / cites work: On the mathematical foundations of learning / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4261789 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4303351 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The consistency of multicategory support vector machines / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Local error estimates for radial basis function interpolation of scattered data / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Shannon sampling. II: Connections to learning theory / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q3093293 / rank | |||
Normal rank |
Latest revision as of 13:54, 28 June 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Behavior of a functional in learning theory |
scientific article |
Statements
Behavior of a functional in learning theory (English)
0 references
29 July 2008
0 references
Let \(A:H\to H\) be a continuous linear operator on a Hilbert space \(H\), \(R(A)\) the range of \(A\), and let \(y\in H\) satisfy \(y\in\overline{R(A)}\) and \(y\notin R(A)\). The author studies the functional \(F(\tau)\) defined as \(\inf\{\|y-Ax\|^2:x\in H,\|x\|\leq\tau\}\), \(\tau\geq 0\). Assuming that \(y\in R((AA^*)^{t/2})\) for some \(0<t<1\) he proves that \(F(\tau)\leq\tau^{-\frac{2t}{1-t}}\|(AA^*)^{-\frac 12}y\|^{\frac{2}{1-t}}\), \(\forall\tau>0\).
0 references