Jonathan W. Siegel

activity

20192024

most citedSharp Bounds on the Approximation Rates, Metric Entropy, and

n

-widths of Shallow Neural Networks

60 citations · 202 across the 22 of their papers we have counts for

collaborators

Showing 2022Show all

2 papers · 1 filter

stat.ML2022★ 9 cited

Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces

Jonathan W. Siegel

Let $Ω = [0, 1]^{d}$ be the unit cube in $R^{d}$ . We study the problem of how efficiently, in terms of the number of parameters, deep neural networks with the ReLU activation fu…

cs.LG2022★ 9 cited

On the Activation Function Dependence of the Spectral Bias of Neural Networks

Qingguo Hong, Jonathan W. Siegel, Qinyang Tan +1

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of vie…