Alert button
Picture for Mingyi Hong

Mingyi Hong

Alert button

Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond

Jan 14, 2020
Tsung-Hui Chang, Mingyi Hong, Hoi-To Wai, Xinwei Zhang, Songtao Lu

Figure 1 for Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
Figure 2 for Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
Figure 3 for Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
Figure 4 for Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
Viaarxiv icon

A Communication Efficient Vertical Federated Learning Framework

Dec 27, 2019
Yang Liu, Yan Kang, Xinwei Zhang, Liping Li, Yong Cheng, Tianjian Chen, Mingyi Hong, Qiang Yang

Figure 1 for A Communication Efficient Vertical Federated Learning Framework
Figure 2 for A Communication Efficient Vertical Federated Learning Framework
Viaarxiv icon

Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms

Dec 16, 2019
Seyed Amir Hossein Hosseini, Burhaneddin Yaman, Steen Moeller, Mingyi Hong, Mehmet Akçakaya

Figure 1 for Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms
Figure 2 for Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms
Figure 3 for Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms
Figure 4 for Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms
Viaarxiv icon

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

Oct 16, 2019
Xiangyi Chen, Sijia Liu, Kaidi Xu, Xingguo Li, Xue Lin, Mingyi Hong, David Cox

Figure 1 for ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Figure 2 for ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Figure 3 for ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Figure 4 for ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Viaarxiv icon

Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach

Oct 13, 2019
Haoran Sun, Songtao Lu, Mingyi Hong

Figure 1 for Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach
Figure 2 for Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach
Viaarxiv icon

On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost

Jul 14, 2019
Zhuoran Yang, Yongxin Chen, Mingyi Hong, Zhaoran Wang

Viaarxiv icon

SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems

Jul 09, 2019
Songtao Lu, Meisam Razaviyayn, Bo Yang, Kejun Huang, Mingyi Hong

Figure 1 for SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
Figure 2 for SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
Figure 3 for SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
Figure 4 for SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
Viaarxiv icon

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Jun 10, 2019
Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin

Figure 1 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 2 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 3 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 4 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Viaarxiv icon

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Jun 06, 2019
Xiangyi Chen, Tiancong Chen, Haoran Sun, Zhiwei Steven Wu, Mingyi Hong

Figure 1 for Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
Figure 2 for Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
Figure 3 for Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
Viaarxiv icon