Error bounds for suboptimal solutions to kernel principal component analysis
From MaRDI portal
Publication:968012
DOI10.1007/S11590-009-0158-1zbMath1189.90153OpenAlexW2087766174MaRDI QIDQ968012
Giorgio Gnecco, Marcello Sanguineti
Publication date: 3 May 2010
Published in: Optimization Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s11590-009-0158-1
Related Items (4)
On spectral windows in supervised learning from data ⋮ Robust kernel principal component analysis with optimal mean ⋮ Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints ⋮ Functional optimization by variable-basis approximation schemes
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Accuracy of suboptimal solutions to kernel principal component analysis
- The Hoffman-Wielandt inequality in infinite dimensions
- Random matrix approximation of spectra of integral operators
- Algorithms with high order convergence speed for blind source extraction
- Universal approximation bounds for superpositions of a sigmoidal function
- Comparison of worst case errors in linear and neural network approximation
- Error Estimates for Approximate Optimization by the Extended Ritz Method
- Theory of Reproducing Kernels
This page was built for publication: Error bounds for suboptimal solutions to kernel principal component analysis
