On the rates of nonlinear and linear approximation

On the rates of nonlinear and linear approximation

Abstract

Motivated by the remarkable performance of nonlinear approximation schemes in the solution od complex problems (e.g. functional optimization problems from control theory, text pronounciation, etc.), we discuss some issues on the rates of approximation by linear and nonlinear approximators in certain spaces of functions. We demontrate some qualitative arguments which support better experimental performance of nonlinear approximators with respect to the linear ones. Finally, using the concept of variation of a function with respect to a set, we present bounds to the rate of the approximation error achievable by nonlinear approximators in certain spaces of functions and show that they are better than the rates achieved by linear approximation in the same spaces. This motivates using the nonlinear approximators for solving complex problems.

Grafik Top
Authors
  • Hlavackova-Schindler, Katerina
  • Sanguineti, Marcello
Grafik Top
Editors
  • Rojicek, J.,
  • Valeckova, M.,
  • Karny, M.,
  • Warwick, K.,
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
3rd European IEEE Workshop CMP'98
Divisions
Data Mining and Machine Learning
Subjects
Theoretische Informatik
Event Location
Prague, Czechia
Event Type
Workshop
Event Dates
September 7-9, 1998
Series Name
Computer-Intensive Methods in Control and Data Processing: Can We Beat the Curse of Dimensionality?
Page Range
pp. 211-216
Date
7 September 1998
Export
Grafik Top