Picture for Zhenxun Zhuang

Zhenxun Zhuang

Adaptive Strategies in Non-convex Optimization

Add code
Jun 17, 2023
Viaarxiv icon

Robustness to Unbounded Smoothness of Generalized SignSGD

Add code
Aug 23, 2022
Figure 1 for Robustness to Unbounded Smoothness of Generalized SignSGD
Figure 2 for Robustness to Unbounded Smoothness of Generalized SignSGD
Figure 3 for Robustness to Unbounded Smoothness of Generalized SignSGD
Figure 4 for Robustness to Unbounded Smoothness of Generalized SignSGD
Viaarxiv icon

A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks

Add code
May 10, 2022
Figure 1 for A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
Figure 2 for A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
Figure 3 for A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
Figure 4 for A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
Viaarxiv icon

Understanding AdamW through Proximal Methods and Scale-Freeness

Add code
Jan 31, 2022
Figure 1 for Understanding AdamW through Proximal Methods and Scale-Freeness
Figure 2 for Understanding AdamW through Proximal Methods and Scale-Freeness
Figure 3 for Understanding AdamW through Proximal Methods and Scale-Freeness
Figure 4 for Understanding AdamW through Proximal Methods and Scale-Freeness
Viaarxiv icon

Exponential Step Sizes for Non-Convex Optimization

Add code
Feb 12, 2020
Figure 1 for Exponential Step Sizes for Non-Convex Optimization
Figure 2 for Exponential Step Sizes for Non-Convex Optimization
Figure 3 for Exponential Step Sizes for Non-Convex Optimization
Figure 4 for Exponential Step Sizes for Non-Convex Optimization
Viaarxiv icon

Online Meta-Learning on Non-convex Setting

Add code
Oct 22, 2019
Figure 1 for Online Meta-Learning on Non-convex Setting
Viaarxiv icon

Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization

Add code
Jan 25, 2019
Figure 1 for Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
Figure 2 for Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
Figure 3 for Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
Figure 4 for Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
Viaarxiv icon