ℓ1 Regularization in Infinite Dimensional Feature Spaces

DOI10.1007/978-3-540-72927-3_39MaRDI QIDQ5434074zbMATH OpenOpenAlexFDO

Authors Saharon Rosset, Grzegorz Świrszcz, Nathan Srebro, Ji Zhu

Publication date 3 January 2008

Published in Learning Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-540-72927-3_39

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• An approximation theory approach to learning with \(\ell^1\) regularization
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Efficient global approximation of generalized nonlinear \(\ell _{1}\)-regularized solution paths and its applications
• Piecewise linear regularized solution paths
• An interior-point method for large-scale l₁-regularized logistic regression

Cited in

(14)

• Understanding neural networks with reproducing kernel Banach spaces
• Generalization bounds for sparse random feature expansions
• Challenges in optimization with complex PDE-systems. Abstracts from the workshop held February 14--20, 2021 (hybrid meeting)
• Degrees of freedom for off-the-grid sparse estimation
• Nonconvex regularization for sparse neural networks
• Testing Gaussian process with applications to super-resolution
• Efficient global approximation of generalized nonlinear \(\ell _{1}\)-regularized solution paths and its applications
• Learning with infinitely many features
• Saturating splines and feature selection
• Banach space representer theorems for neural networks and ridge splines
• scientific article; zbMATH DE number 7626727 (Why is no real title available?)
• Two steps at a time-taking GAN training in stride with Tseng's method
• MARS via lasso
• Function-space optimality of neural architectures with multivariate nonlinearities

This page was built for publication: ℓ1 Regularization in Infinite Dimensional Feature Spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5434074)