Learning non-parametric basis independent models from point queries via low-rank methods

DOI10.1016/j.acha.2014.01.002zbMath1373.68336arXiv1310.1826OpenAlexW2012411663MaRDI QIDQ741260

Hemant Tyagi, Volkan Cevher

Publication date: 11 September 2014

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

Full work available at URL: https://arxiv.org/abs/1310.1826

zbMATH Keywords

nonlinear approximationlow-rank matrix recoveryhigh-dimensional function approximationmulti-ridge functionsoracle-based learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (15)

Certified dimension reduction in nonlinear Bayesian inverse problems ⋮ Multifidelity Dimension Reduction via Active Subspaces ⋮ Global optimization using random embeddings ⋮ Bound-constrained global optimization of functions with low effective dimensionality using multiple random embeddings ⋮ The recovery of ridge functions on the hypercube suffers from the curse of dimensionality ⋮ Matrix recipes for hard thresholding methods ⋮ Data-Driven Polynomial Ridge Approximation Using Variable Projection ⋮ Embedded ridge approximations ⋮ On recovery of regular ridge functions ⋮ Dimension Reduction via Gaussian Ridge Functions ⋮ Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments ⋮ A near-stationary subspace for ridge approximation ⋮ Gaussian Quadrature and Polynomial Approximation for One-Dimensional Ridge Functions ⋮ Recovery of regular ridge functions on the ball ⋮ On two continuum armed bandit problems in high dimensions

Uses Software

• hgam
• ADMiRA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning functions of few arbitrary linear parameters in high dimensions
• Sparsity in multiple kernel learning
• On almost linearity of low dimensional projections from high dimensional data
• Component selection and smoothing in multivariate nonparametric regression
• Projection-based approximation and a duality with kernel methods
• High-dimensional additive modeling
• Projection pursuit
• Optimal reconstruction of a function from its projections
• Harmonic analysis of neural networks
• Ridgelets: estimating with ridge functions
• Adaptive estimation of a quadratic functional by model selection.
• Approximation of infinitely differentiable multivariate functions is intractable
• Capturing ridge functions in high dimensions from point queries
• Exact matrix completion via convex optimization
• Robust principal component analysis?
• Minimal Errors for Strong and Weak Approximation of Stochastic Differential Equations
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Sliced Inverse Regression for Dimension Reduction
• Rank one perturbation and its application to the laplacian spectrum of a graph^∗
• Sparse Additive Models
• An Adaptive Estimation of Dimension Reduction Space
• Ridgelets: a key to higher-dimensional intermittency?
• ADMiRA: Atomic Decomposition for Minimum Rank Approximation
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• A Multiple-Index Model and Dimension Reduction
• Perturbation bounds in connection with singular value decomposition

This page was built for publication: Learning non-parametric basis independent models from point queries via low-rank methods