Accuracy of suboptimal solutions to kernel principal component analysis
From MaRDI portal
Publication:842769
DOI10.1007/S10589-007-9108-YzbMath1179.90325OpenAlexW1963979070MaRDI QIDQ842769
Giorgio Gnecco, Marcello Sanguineti
Publication date: 25 September 2009
Published in: Computational Optimization and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10589-007-9108-y
Lagrangiankernel methodsprincipal component analysis (PCA)primal and dual problemssuboptimal solutionsregularized optimization problems
Related Items (11)
On spectral windows in supervised learning from data ⋮ Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints ⋮ A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization ⋮ Can dictionary-based computational models outperform the best linear ones? ⋮ New insights into Witsenhausen's counterexample ⋮ Team optimization problems with Lipschitz continuous strategies ⋮ Functional optimization by variable-basis approximation schemes ⋮ Error bounds for suboptimal solutions to kernel principal component analysis ⋮ Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling ⋮ The weight-decay technique in learning from data: an optimization point of view ⋮ Convex combination of data matrices: PCA perturbation bounds for multi-objective optimal design of mechanical metafilters
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Learning with generalization capability by kernel methods of bounded complexity
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Support-vector networks
- Relationship of several variational methods for the approximate solution of ill-posed problems
- On the mathematical foundations of learning
- Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
- An Approach to Time Series Analysis
- On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
- Universal approximation bounds for superpositions of a sigmoidal function
- Bounds on rates of variable-basis and neural-network approximation
- 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: Accuracy of suboptimal solutions to kernel principal component analysis
