On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions
From MaRDI portal
Publication:5361284
zbMath1435.65045arXiv1502.06800MaRDI QIDQ5361284
Publication date: 27 September 2017
Full work available at URL: https://arxiv.org/abs/1502.06800
Related Items
Randomized numerical linear algebra: Foundations and algorithms, Spurious Valleys in Two-layer Neural Network Optimization Landscapes, Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration, Generalization properties of doubly stochastic learning algorithms, Optimal Quadrature-Sparsification for Integral Operator Approximation, Unnamed Item, Unnamed Item, Compressive statistical learning with random feature moments, HARFE: hard-ridge random feature expansion, Transferable neural networks for partial differential equations, Unnamed Item, Unnamed Item, Learning to Forecast Dynamical Systems from Streaming Data, Benign Overfitting and Noisy Features, Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition, Maximum Likelihood Estimation and Uncertainty Quantification for Gaussian Process Approximation of Deterministic Functions, Unnamed Item, Unnamed Item, Unnamed Item, On b-bit min-wise hashing for large-scale regression and classification with sparse data, The Hardness of Conditional Independence Testing and the Generalised Covariance Measure, Linearized two-layers neural networks in high dimension, Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings, The Random Feature Model for Input-Output Maps between Banach Spaces, Symmetry exploits for Bayesian cubature methods, Fast generalization error bound of deep learning without scale invariance of activation functions, Supervised learning from noisy observations: combining machine-learning techniques with data assimilation, Bayesian Approximate Kernel Regression With Variable Selection, Convolutional spectral kernel learning with generalization guarantees, Unnamed Item, Unnamed Item, A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
