Author of the publication

A Fine-Grained Spectral Perspective on Neural Networks

, and . (2019)cite arxiv:1907.10599Comment: 12 pages of main text, 14 figures, 39 pages including appendix.

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

A Homological Theory of Functions. (2017)cite arxiv:1701.02302Comment: 72 pages, 22 figures. Comments welcome.Free resolutions of function classes via order complexes., , , and . CoRR, (2019)A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks., , , , and . NeurIPS, page 9832-9842. (2019)Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers., , , , , , and . NeurIPS, page 11289-11300. (2019)Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation. (2019)cite arxiv:1902.04760Comment: tldr: A theoretical tool for understanding the behavior of large width randomly initialized neural networks for almost all deep learning architectures.Tensor Programs III: Neural Matrix Laws.. CoRR, (2020)Lie-Access Neural Turing Machines., and . CoRR, (2016)Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes, , , , , , , , and . (2018)cite arxiv:1810.05148Comment: Published as a conference paper at ICLR 2019.A Fine-Grained Spectral Perspective on Neural Networks, and . (2019)cite arxiv:1907.10599Comment: 12 pages of main text, 14 figures, 39 pages including appendix.Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes. (2019)cite arxiv:1910.12478Comment: Appearing in NeurIPS 2019; 10 pages of main text; 12 figures, 11 programs; 73 pages total.