Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
1905.07777
Cited By
v1
v2
v3 (latest)
A type of generalization error induced by initialization in deep neural networks
Mathematical and Scientific Machine Learning (MSML), 2019
19 May 2019
Yaoyu Zhang
Zhi-Qin John Xu
Yaoyu Zhang
Zheng Ma
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"A type of generalization error induced by initialization in deep neural networks"
32 / 32 papers shown
From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
Zheng-an Chen
Tao Luo
AI4CE
143
1
0
08 Oct 2025
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
Neural Information Processing Systems (NeurIPS), 2023
Moritz Haas
David Holzmüller
U. V. Luxburg
Ingo Steinwart
MLT
392
23
0
23 May 2023
Omnigrok: Grokking Beyond Algorithmic Data
International Conference on Learning Representations (ICLR), 2022
Ziming Liu
Eric J. Michaud
Max Tegmark
367
111
0
03 Oct 2022
Why neural networks find simple solutions: the many regularizers of geometric complexity
Neural Information Processing Systems (NeurIPS), 2022
Benoit Dherin
Michael Munn
M. Rosca
David Barrett
351
43
0
27 Sep 2022
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
International Conference on Machine Learning (ICML), 2022
Chuan Wen
Jianing Qian
Jierui Lin
Jiaye Teng
Dinesh Jayaraman
Yang Gao
AAML
218
21
0
22 Jun 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
Neural Information Processing Systems (NeurIPS), 2022
Benjamin Bowman
Guido Montúfar
270
17
0
06 Jun 2022
Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width
Neural Information Processing Systems (NeurIPS), 2022
Hanxu Zhou
Qixuan Zhou
Zhenyuan Jin
Yaoyu Zhang
Yaoyu Zhang
Zhi-Qin John Xu
238
22
0
24 May 2022
Towards Understanding Grokking: An Effective Theory of Representation Learning
Neural Information Processing Systems (NeurIPS), 2022
Ziming Liu
O. Kitouni
Niklas Nolte
Eric J. Michaud
Max Tegmark
Mike Williams
AI4CE
322
206
0
20 May 2022
Limitation of Characterizing Implicit Regularization by Data-independent Functions
Leyang Zhang
Z. Xu
Yaoyu Zhang
Yaoyu Zhang
169
0
0
28 Jan 2022
Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions
Mojtaba Sahraee-Ardakan
M. Emami
Parthe Pandit
S. Rangan
A. Fletcher
201
9
0
20 Jan 2022
Overview frequency principle/spectral bias in deep learning
Communication on Applied Mathematics and Computation (CAMC), 2022
Z. Xu
Yaoyu Zhang
Yaoyu Zhang
FaML
357
119
0
19 Jan 2022
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks
International Conference on Learning Representations (ICLR), 2022
Benjamin Bowman
Guido Montúfar
206
13
0
12 Jan 2022
Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks
Journal of machine learning research (JMLR), 2021
Aleksandr Shevchenko
Vyacheslav Kungurtsev
Marco Mondelli
MLT
288
15
0
03 Nov 2021
Quantifying Epistemic Uncertainty in Deep Learning
Ziyi Huang
Henry Lam
Haofeng Zhang
UQCV
BDL
UD
PER
417
15
0
23 Oct 2021
AdjointNet: Constraining machine learning models with physics-based codes
S. Karra
B. Ahmmed
M. Mudunuru
AI4CE
PINN
OOD
159
4
0
08 Sep 2021
A Neural Tangent Kernel Perspective of GANs
International Conference on Machine Learning (ICML), 2021
Jean-Yves Franceschi
Emmanuel de Bézenac
Ibrahim Ayed
Mickaël Chen
Sylvain Lamprier
Patrick Gallinari
494
29
0
10 Jun 2021
Embedding Principle of Loss Landscape of Deep Neural Networks
Neural Information Processing Systems (NeurIPS), 2021
Yaoyu Zhang
Zhongwang Zhang
Yaoyu Zhang
Z. Xu
242
42
0
30 May 2021
Towards Understanding the Condensation of Neural Networks at Initial Training
Neural Information Processing Systems (NeurIPS), 2021
Hanxu Zhou
Qixuan Zhou
Yaoyu Zhang
Yaoyu Zhang
Z. Xu
MLT
AI4CE
373
32
0
25 May 2021
An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network
Mathematical and Scientific Machine Learning (MSML), 2021
Yaoyu Zhang
Zheng Ma
Zhiwei Wang
Z. Xu
Yaoyu Zhang
255
5
0
25 May 2021
How Fine-Tuning Allows for Effective Meta-Learning
Neural Information Processing Systems (NeurIPS), 2021
Kurtland Chua
Qi Lei
Jason D. Lee
233
55
0
05 May 2021
Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning
Yaoyu Zhang
Zheng Ma
Zhiwei Wang
Zhi-Qin John Xu
Yaoyu Zhang
OOD
256
4
0
06 Dec 2020
Which Minimizer Does My Neural Network Converge To?
Manuel Nonnenmacher
David Reeb
Ingo Steinwart
ODL
193
5
0
04 Nov 2020
On the exact computation of linear frequency principle dynamics and its generalization
Yaoyu Zhang
Zheng Ma
Z. Xu
Yaoyu Zhang
185
23
0
15 Oct 2020
Implicit Gradient Regularization
International Conference on Learning Representations (ICLR), 2020
David Barrett
Benoit Dherin
364
172
0
23 Sep 2020
Finite Versus Infinite Neural Networks: an Empirical Study
Neural Information Processing Systems (NeurIPS), 2020
Jaehoon Lee
S. Schoenholz
Jeffrey Pennington
Ben Adlam
Lechao Xiao
Roman Novak
Jascha Narain Sohl-Dickstein
310
227
0
31 Jul 2020
Deep frequency principle towards understanding why deeper learning is faster
AAAI Conference on Artificial Intelligence (AAAI), 2020
Zhi-Qin John Xu
Hanxu Zhou
244
59
0
28 Jul 2020
Phase diagram for two-layer ReLU neural networks at infinite-width limit
Journal of machine learning research (JMLR), 2020
Yaoyu Zhang
Zhi-Qin John Xu
Zheng Ma
Yaoyu Zhang
212
71
0
15 Jul 2020
Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
Yaoyu Zhang
Haizhao Yang
398
84
0
28 Jun 2020
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Wei Hu
Lechao Xiao
Ben Adlam
Jeffrey Pennington
194
69
0
25 Jun 2020
A priori generalization error for two-layer ReLU neural network through minimum norm solution
Zhi-Qin John Xu
Jiwei Zhang
Yaoyu Zhang
Chengchao Zhao
MLT
167
1
0
06 Dec 2019
Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks
Yaoyu Zhang
Zhi-Qin John Xu
Yaoyu Zhang
Zheng Ma
MLT
AI4CE
247
43
0
24 May 2019
Training behavior of deep neural network in frequency domain
International Conference on Neural Information Processing (ICONIP), 2018
Zhi-Qin John Xu
Yaoyu Zhang
Yan Xiao
AI4CE
539
374
0
03 Jul 2018
1
