Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality

2 September 2022

Papers citing "Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality"

6 / 6 papers shown

Title
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias Jiyoung Park Ian Pelakh Stephan Wojtowytsch 42 2 0 10 Nov 2023
Optimization-Based Separations for Neural Networks Itay Safran Jason D. Lee 137 14 0 04 Dec 2021
Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions Boris Hanin MLT 38 9 0 27 Sep 2021
A Note on the Representation Power of GHHs Zhou Lu 22 5 0 27 Jan 2021
$Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ \ell^1 $ and $ \ell^0 $ Controls$ Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $\ell^1$ and $\ell^0$ Controls Jason M. Klusowski Andrew R. Barron 130 142 0 26 Jul 2016
Benefits of depth in neural networks Matus Telgarsky 148 602 0 14 Feb 2016