Generalization Performance of Some Learning Problems in Hilbert Functional Spaces
نویسنده
چکیده
We investigate the generalization performance of some learning problems in Hilbert functional Spaces. We introduce a notion of convergence of the estimated functional predictor to the best underlying predictor, and obtain an estimate on the rate of the convergence. This estimate allows us to derive generalization bounds on some learning formulations.
منابع مشابه
$G$-Frames for operators in Hilbert spaces
$K$-frames as a generalization of frames were introduced by L. Gu{a}vruc{t}a to study atomic systems on Hilbert spaces which allows, in a stable way, to reconstruct elements from the range of the bounded linear operator $K$ in a Hilbert space. Recently some generalizations of this concept are introduced and some of its difference with ordinary frames are studied. In this paper, we give a new ge...
متن کاملEffective Dimension and Generalization of Kernel Learning
We investigate the generalization performance of some learning problems in Hilbert function Spaces. We introduce a concept of scalesensitive effective data dimension, and show that it characterizes the convergence rate of the underlying learning problem. Using this concept, we can naturally extend results for parametric estimation problems in finite dimensional spaces to non-parametric kernel l...
متن کاملSome Properties of Continuous $K$-frames in Hilbert Spaces
The theory of continuous frames in Hilbert spaces is extended, by using the concepts of measure spaces, in order to get the results of a new application of operator theory. The $K$-frames were introduced by G$breve{mbox{a}}$vruta (2012) for Hilbert spaces to study atomic systems with respect to a bounded linear operator. Due to the structure of $K$-frames, there are many differences between...
متن کاملWoven fusion frames in Hilbert spaces and some of their properties
Extending and improving the concepts: woven frame and fusion frames, we introduce the notion of woven fusion frames in Hilbert spaces. We clarify our extension and generalization by some examples of woven frames and woven fusion frames. Also, we present some properties of woven fusion frames, especially we show that for given two woven frames of sequences, one can build woven fusion frames and ...
متن کاملGeneralization of Canonical Correlation Analysis from Multivariate to Functional Cases and its related problems
In multivariate cases, the aim of canonical correlation analysis (CCA) for two sets of variables x and y is to obtain linear combinations of them so that they have the largest possible correlation. However, when x and y are continouse functions of another variable (generally time) in nature, these two functions belong to function spaces which are of infinite dimension, and CCA for them should b...
متن کامل