Følg
Jonathan W. Siegel
Jonathan W. Siegel
Assistant Professor, Texas A&M University
Verifisert e-postadresse på tamu.edu - Startside
Tittel
Sitert av
Sitert av
År
Approximation rates for neural networks with general activation functions
JW Siegel, J Xu
Neural Networks 128, 313-321, 2020
1932020
Sharp Bounds on the Approximation Rates, Metric Entropy, and n-Widths of Shallow Neural Networks
JW Siegel, J Xu
Foundations of Computational Mathematics 24 (2), 481-537, 2024
99*2024
Greedy Training Algorithms for Neural Networks and Applications to PDEs
JW Siegel, Q Hong, X Jin, W Hao, J Xu
Journal of Computational Physics, 112084, 2023
99*2023
High-order approximation rates for shallow neural networks with cosine and ReLUk activation functions
JW Siegel, J Xu
Applied and Computational Harmonic Analysis 58, 1-26, 2022
92*2022
Characterization of the variation spaces corresponding to shallow neural networks
JW Siegel, J Xu
Constructive Approximation 57 (3), 1109-1132, 2023
562023
Accelerated first-order methods: Differential equations and Lyapunov functions
JW Siegel
arXiv preprint arXiv:1903.05671, 2019
552019
Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces
JW Siegel
Journal of Machine Learning Research 24 (357), 1-52, 2023
48*2023
Extensible Structure-informed prediction of formation energy with improved accuracy and usability employing neural networks
AM Krajewski, JW Siegel, J Xu, ZK Liu
Computational Materials Science 208, 111254, 2022
412022
On the activation function dependence of the spectral bias of neural networks
Q Hong, JW Siegel, Q Tan, J Xu
arXiv preprint arXiv:2208.04924, 2022
342022
Optimal convergence rates for the orthogonal greedy algorithm
JW Siegel, J Xu
IEEE Transactions on Information Theory 68 (5), 3354-3361, 2022
30*2022
Accelerated optimization with orthogonality constraints
JW Siegel
arXiv preprint arXiv:1903.05204, 2019
242019
Uniform approximation rates and metric entropy of shallow neural networks
L Ma, JW Siegel, J Xu
Research in the Mathematical Sciences 9 (3), 46, 2022
172022
Equivariant Frames and the Impossibility of Continuous Canonicalization
N Dym, H Lawrence, JW Siegel
arXiv preprint arXiv:2402.16077, 2024
162024
Entropy-based convergence rates of greedy algorithms
Y Li, J Siegel
arXiv preprint arXiv:2304.13332, 2023
102023
Weighted variation spaces and approximation by shallow ReLU networks
R DeVore, RD Nowak, R Parhi, JW Siegel
Applied and Computational Harmonic Analysis, 101713, 2024
72024
On the expressiveness and spectral bias of KANs
Y Wang, JW Siegel, Z Liu, TY Hou
arXiv preprint arXiv:2410.01803, 2024
72024
Training Sparse Neural Networks using Compressed Sensing
JW Siegel, J Chen, P Zhang, J Xu
arXiv preprint arXiv:2008.09661, 2020
72020
Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks
JW Siegel
arXiv preprint arXiv:2307.15285, 2023
62023
A qualitative difference between gradient flows of convex functions in finite-and infinite-dimensional Hilbert spaces
JW Siegel, S Wojtowytsch
Explorations in the Mathematics of Data Science: The Inaugural Volume of the …, 2024
52024
Nesterov acceleration despite very noisy gradients
K Gupta, JW Siegel, S Wojtowytsch
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 0
5*
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20