Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data
From MaRDI portal
Publication:3556804
DOI10.1162/neco.2009.05-08-786zbMath1200.68130WikidataQ33516154 ScholiaQ33516154MaRDI QIDQ3556804
Giorgio Gnecco, Marcello Sanguineti
Publication date: 26 April 2010
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.2009.05-08-786
68Q32: Computational learning theory
Related Items
Learning with Boundary Conditions, Levenberg-Marquardt multi-classification using hinge loss function, Sign stochastic gradient descents without bounded gradient assumption for the finite sum minimization, Can dictionary-based computational models outperform the best linear ones?, Functional optimization by variable-basis approximation schemes, On spectral windows in supervised learning from data, An algorithm for curve identification in the presence of curve intersections, Laplacian twin support vector machine for semi-supervised classification, Alternating step size method for solving ill-posed linear operator equations in energetic space, Distributed semi-supervised support vector machines
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Learning with generalization capability by kernel methods of bounded complexity
- Well-posed optimization problems
- Elastic-net regularization in learning theory
- Best choices for regularization parameters in learning theory: on the bias-variance problem.
- Least angle regression. (With discussion)
- Random approximants and neural networks
- Regularization networks and support vector machines
- Relationship of several variational methods for the approximate solution of ill-posed problems
- On the mathematical foundations of learning
- Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and Convergence
- On the exponential convergence of matching pursuits in quasi-incoherent dictionaries
- Greed is Good: Algorithmic Results for Sparse Approximation
- Bounds on rates of variable-basis and neural-network approximation
- Comparison of worst case errors in linear and neural network approximation
- Sequential greedy approximation for certain convex optimization problems
- Structural risk minimization over data-dependent hierarchies
- 10.1162/153244302760200704
- Approximation Bounds for Some Sparse Kernel Regression Algorithms
- 10.1162/153244303321897690
- Regularization and Variable Selection Via the Elastic Net
- Error Estimates for Approximate Optimization by the Extended Ritz Method
- Least Squares Methods for Ill-Posed Problems with a Prescribed Bound
- Neural Network Learning as an Inverse Problem
- Kernel matching pursuit
- Adaptive greedy approximations