Follow
Behrooz Ghorbani
Behrooz Ghorbani
Researcher, OpenAI
Verified email at stanford.edu - Homepage
Title
Cited by
Cited by
Year
An investigation into neural net optimization via hessian eigenvalue density
B Ghorbani, S Krishnan, Y Xiao
International Conference on Machine Learning, 2232-2241, 2019
2842019
Linearized two-layers neural networks in high dimension
B Ghorbani, S Mei, T Misiakiewicz, A Montanari
The Annals of Statistics 49 (2), 1029-1054, 2021
2232021
When do neural networks outperform kernel methods?
B Ghorbani, S Mei, T Misiakiewicz, A Montanari
Advances in Neural Information Processing Systems 33, 2020
1722020
Limitations of lazy training of two-layers neural network
B Ghorbani, S Mei, T Misiakiewicz, A Montanari
Advances in Neural Information Processing Systems, 9111-9121, 2019
1382019
Scaling Laws for Neural Machine Translation
B Ghorbani, O Firat, M Freitag, A Bapna, M Krikun, X Garcia, C Chelba, ...
arXiv preprint arXiv:2109.07740, 2021
682021
Do Current Multi-Task Optimization Methods in Deep Learning Even Help?
D Xin, B Ghorbani, J Gilmer, A Garg, O Firat
Advances in Neural Information Processing Systems 35, 13597-13609, 2022
362022
Adaptive Gradient Methods at the Edge of Stability
JM Cohen, B Ghorbani, S Krishnan, N Agarwal, S Medapati, M Badura, ...
arXiv preprint arXiv:2207.14484, 2022
362022
An instability in variational inference for topic models
B Ghorbani, H Javadi, A Montanari
International Conference on Machine Learning, 2221-2231, 2019
352019
Data Scaling Laws in NMT: The Effect of Noise and Architecture
Y Bansal, B Ghorbani, A Garg, B Zhang, C Cherry, B Neyshabur, O Firat
International Conference on Machine Learning, 1466-1482, 2022
312022
A Loss Curvature Perspective on Training Instability in Deep Learning
J Gilmer, B Ghorbani, A Garg, S Kudugunta, B Neyshabur, D Cardoze, ...
arXiv preprint arXiv:2110.04369, 2021
262021
A Loss Curvature Perspective on Training Instabilities of Deep Learning Models
J Gilmer, B Ghorbani, A Garg, S Kudugunta, B Neyshabur, D Cardoze, ...
International Conference on Learning Representations, 2021
242021
Scaling laws for multilingual neural machine translation
P Fernandes, B Ghorbani, X Garcia, M Freitag, O Firat
International Conference on Machine Learning, 10053-10071, 2023
132023
Epsilon Sampling Rocks: Investigating Sampling Strategies for\\Minimum Bayes Risk Decoding for Machine Translation
M Freitag, B Ghorbani, P Fernandes
arXiv preprint arXiv:2305.09860, 2023
122023
Examining scaling and transfer of language model architectures for machine translation
B Zhang, B Ghorbani, A Bapna, Y Cheng, X Garcia, J Shen, O Firat
International Conference on Machine Learning, 26176-26192, 2022
122022
Discussion of:“Nonparametric regression using deep neural networks with ReLU activation function”
B Ghorbani, S Mei, T Misiakiewicz, A Montanari
The Annals of Statistics 48 (4), 1898-1901, 2020
82020
Optimal Covariance Estimation for Condition Number Loss in the Spiked Model
DL Donoho, B Ghorbani
arXiv preprint arXiv:1810.07403, 2018
82018
Binarized Neural Machine Translation
Y Zhang, A Garg, Y Cao, L Lew, B Ghorbani, Z Zhang, O Firat
Advances in Neural Information Processing Systems 36, 2024
42024
The effect of network depth on the optimization landscape
B Ghorbani, Y Xiao, S Krishnan
ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena, 2019
32019
A loss curvature perspective on training instability in deep learning
J Gilmer, B Ghorbani, A Garg, SR Kudugunta, B Neyshabur, D Cardoze, ...
12022
Order Matters in the Presence of Dataset Imbalance for Multilingual Learning
D Choi, D Xin, H Dadkhahi, J Gilmer, A Garg, O Firat, CK Yeh, AM Dai, ...
Thirty-seventh Conference on Neural Information Processing Systems, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–20