Greg Yang
Greg Yang
Microsoft Research
Bestätigte E-Mail-Adresse bei microsoft.com
Titel
Zitiert von
Zitiert von
Jahr
Provably robust deep learning via adversarially trained smoothed classifiers
H Salman, J Li, I Razenshteyn, P Zhang, H Zhang, S Bubeck, G Yang
Advances in Neural Information Processing Systems, 11292-11303, 2019
1212019
Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation
G Yang
arXiv preprint arXiv:1902.04760, 2019
1092019
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
R Novak, L Xiao, Y Bahri, J Lee, G Yang, DA Abolafia, J Pennington, ...
1042018
Mean Field Residual Networks: On the Edge of Chaos
G Yang, S Schoenholz
Advances in neural information processing systems, 7103-7114, 2017
972017
A mean field theory of batch normalization
G Yang, J Pennington, V Rao, J Sohl-Dickstein, SS Schoenholz
arXiv preprint arXiv:1902.08129, 2019
822019
A convex relaxation barrier to tight robustness verification of neural networks
H Salman, G Yang, H Zhang, CJ Hsieh, P Zhang
Advances in Neural Information Processing Systems, 9835-9846, 2019
462019
A Fine-Grained Spectral Perspective on Neural Networks
G Yang, H Salman
arXiv preprint arXiv:1907.10599, 2019
282019
Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
G Yang
Advances in Neural Information Processing Systems, 9947-9960, 2019
27*2019
Randomized Smoothing of All Shapes and Sizes
G Yang, T Duan, E Hu, H Salman, I Razenshteyn, J Li
arXiv preprint arXiv:2002.08118, 2020
152020
NAIL: A General Interactive Fiction Agent
M Hausknecht, R Loynd, G Yang, A Swaminathan, JD Williams
arXiv preprint arXiv:1902.04259, 2019
142019
Lie access neural Turing machine
G Yang
arXiv preprint arXiv:1602.08671, 2016
122016
Black-box Smoothing: A Provable Defense for Pretrained Classifiers
H Salman, M Sun, G Yang, A Kapoor, JZ Kolter
arXiv preprint arXiv:2003.01908, 2020
92020
Tensor Programs II: Neural Tangent Kernel for Any Architecture
G Yang
arXiv preprint arXiv:2006.14548, 2020
72020
Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient Explosion
G Yang, SS Schoenholz
62018
Tensor Programs III: Neural Matrix Laws
G Yang
arXiv preprint arXiv:2009.10685, 2020
32020
Improved Image Wasserstein Attacks and Defenses
JE Hu, A Swaminathan, H Salman, G Yang
arXiv preprint arXiv:2004.12478, 2020
32020
Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs
D Gilboa, B Chang, M Chen, G Yang, SS Schoenholz, EH Chi, ...
arXiv preprint arXiv:1901.08987, 2019
32019
A Homological Theory of Functions
G Yang
arXiv preprint arXiv:1701.02302, 2017
32017
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
H Salman, M Sun, G Yang, A Kapoor, JZ Kolter
Advances in Neural Information Processing Systems 33, 2020
22020
Feature Learning in Infinite-Width Neural Networks
G Yang, EJ Hu
arXiv preprint arXiv:2011.14522, 2020
12020
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20