activity
20192022
most citedOn the Activation Function Dependence of the Spectral Bias of Neural Networks

9 citations · 10 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG20229 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…

stat.ML20211 cited

Sharp Lower Bounds on the Approximation Rate of Shallow Neural Networks

Jonathan W. Siegel, Jinchao Xu

We consider the approximation rates of shallow neural networks with respect to the variation norm. Upper bounds on these rates have been established for sigmoidal and ReLU activati…

cs.CV2020

Training Sparse Neural Networks using Compressed Sensing

Jonathan W. Siegel, Jianhong Chen, Pengchuan Zhang +1

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compr…

math.CA2019

Approximation Rates for Neural Networks with General Activation Functions

Jonathan W. Siegel, Jinchao Xu

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer…

math.OC2019

Accelerated First-Order Methods: Differential Equations and Lyapunov Functions

Jonathan W. Siegel

We develop a theory of accelerated first-order optimization from the viewpoint of differential equations and Lyapunov functions. Building upon the previous work of many researchers…

math.OC2019

Accelerated Optimization With Orthogonality Constraints

Jonathan W. Siegel

We develop a generalization of Nesterov's accelerated gradient descent method which is designed to deal with orthogonality constraints. To demonstrate the effectiveness of our meth…