Alert button
Picture for Greg Yang

Greg Yang

Alert button

A Spectral Condition for Feature Learning

Oct 26, 2023
Greg Yang, James B. Simon, Jeremy Bernstein

Viaarxiv icon

Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks

Oct 12, 2023
Greg Yang, Dingli Yu, Chen Zhu, Soufiane Hayou

Figure 1 for Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
Figure 2 for Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
Figure 3 for Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
Figure 4 for Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
Viaarxiv icon

Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit

Aug 07, 2023
Greg Yang, Etai Littwin

Viaarxiv icon

Width and Depth Limits Commute in Residual Networks

Feb 01, 2023
Soufiane Hayou, Greg Yang

Figure 1 for Width and Depth Limits Commute in Residual Networks
Figure 2 for Width and Depth Limits Commute in Residual Networks
Figure 3 for Width and Depth Limits Commute in Residual Networks
Figure 4 for Width and Depth Limits Commute in Residual Networks
Viaarxiv icon

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

May 03, 2022
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang

Figure 1 for High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
Figure 2 for High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
Figure 3 for High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
Figure 4 for High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
Viaarxiv icon

Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Mar 28, 2022
Greg Yang, Edward J. Hu, Igor Babuschkin, Szymon Sidor, Xiaodong Liu, David Farhi, Nick Ryder, Jakub Pachocki, Weizhu Chen, Jianfeng Gao

Figure 1 for Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Figure 2 for Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Figure 3 for Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Figure 4 for Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Viaarxiv icon

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

Nov 04, 2021
Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Christopher Meek, Ahmed Hassan Awadallah, Jianfeng Gao

Figure 1 for CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Figure 2 for CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Figure 3 for CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Figure 4 for CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Viaarxiv icon