Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels

21 May 2020

Papers citing "Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels"

9 / 9 papers shown

Title
Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks Fanghui Liu L. Dadi V. Cevher 74 2 0 29 Apr 2024
Embeddings between Barron spaces with higher order activation functions T. J. Heeringa L. Spek Felix L. Schwenninger C. Brune 21 3 0 25 May 2023
Reinforcement Learning with Function Approximation: From Linear to Nonlinear Jihao Long Jiequn Han 19 5 0 20 Feb 2023
Duality for Neural Networks through Reproducing Kernel Banach Spaces L. Spek T. J. Heeringa Felix L. Schwenninger C. Brune 11 13 0 09 Nov 2022
Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks R. Mojgani Maciej Balajewicz P. Hassanzadeh PINN 25 45 0 05 May 2022
Qualitative neural network approximation over R and C: Elementary proofs for analytic and polynomial activation Josiah Park Stephan Wojtowytsch 15 1 0 25 Mar 2022
Generalization Error of GAN from the Discriminator's Perspective Hongkang Yang Weinan E GAN 38 13 0 08 Jul 2021
Representation formulas and pointwise properties for Barron functions E. Weinan Stephan Wojtowytsch 20 79 0 10 Jun 2020
Can Shallow Neural Networks Beat the Curse of Dimensionality? A mean field training perspective Stephan Wojtowytsch E. Weinan MLT 21 48 0 21 May 2020