Back to Search
Start Over
Approximation of functions from Korobov spaces by shallow neural networks.
- Source :
-
Information Sciences . Jun2024, Vol. 670, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- In this paper, we consider the problem of approximating functions from a Korobov space on [ − 1 , 1 ] d by ReLU shallow neural networks and present a rate O (m − 2 5 (1 + 2 d) log m) of uniform approximation by networks of m hidden neurons. This is achieved by combining a novel Fourier analysis approach and a probability argument. We apply our approximation theory to a learning algorithm for regression based on ReLU shallow neural networks and derive learning rates of order O (N − 4 (d + 2) 9 d + 8 log N) for the excess generalization error with the sample size N when the regression function lies in the Korobov space. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00200255
- Volume :
- 670
- Database :
- Academic Search Index
- Journal :
- Information Sciences
- Publication Type :
- Periodical
- Accession number :
- 177026788
- Full Text :
- https://doi.org/10.1016/j.ins.2024.120573