Generalization bounds for sparse random feature expansions

DOI10.1016/j.acha.2022.08.003zbMath1505.65039arXiv2103.03191OpenAlexW3155603885MaRDI QIDQ2105118

Rachel Ward, Robert Shi, Abolfazl Hashemi, Ufuk Topcu, Hayden Schaeffer, Giang Tran

Publication date: 8 December 2022

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.03191

zbMATH Keywords

compressive sensinggeneralization errorsparse optimizationrandom features

Mathematics Subject Classification ID

Computational learning theory (68Q32) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Algorithms for approximation of functions (65D15)

Related Items (2)

HARFE: hard-ridge random feature expansion ⋮ SPADE4: sparsity and delay embedding based forecasting of epidemics

Uses Software

• UCI-ml
• SPGL1
• glinternet
• UQLab

Cites Work

• Unnamed Item
• Unnamed Item
• A mathematical introduction to compressive sensing
• Learning with infinitely many features
• Sparse Legendre expansions via \(\ell_1\)-minimization
• Learning functions of few arbitrary linear parameters in high dimensions
• A non-adapted sparse approximation of PDEs with stochastic inputs
• Approximation of functions of few variables in high dimensions
• Interpolation via weighted \(\ell_{1}\) minimization
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Infinite-dimensional compressed sensing and function interpolation
• On the computational power of circuits of spiking neurons
• A near-stationary subspace for ridge approximation
• Exploiting active subspaces to quantify uncertainty in the numerical simulation of the hyshot II scramjet
• Bayesian Lasso for Semiparametric Structural Equation Models
• The Perceptron: A Model for Brain Functioning. I
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Probing the Pareto Frontier for Basis Pursuit Solutions
• On decompositions of multivariate functions
• Universal approximation bounds for superpositions of a sigmoidal function
• Extracting Sparse High-Dimensional Dynamics from Limited Data
• Polynomial approximation via compressed sensing of high-dimensional functions on lower sets
• Sparse Additive Models
• On Recovery of Sparse Signals Via $\ell _{1}$ Minimization
• Extracting Structured Dynamical Systems Using Sparse Optimization With Very Few Samples
• ℓ1 Regularization in Infinite Dimensional Feature Spaces
• Stable signal recovery from incomplete and inaccurate measurements
• Compressed sensing

This page was built for publication: Generalization bounds for sparse random feature expansions