activity
20112026
most citedLearning to Optimize: Training Deep Neural Networks for Wireless Resource Management

895 citations · 5.3k across the 104 of their papers we have counts for

collaborators
Showing 2020Show all

15 papers · 1 filter

cs.LG2020★ 9 cited

Hybrid Federated Learning: Algorithms and Implementation

Xinwei Zhang, Wotao Yin, Mingyi Hong +1

Federated learning (FL) is a recently proposed distributed machine learning paradigm dealing with distributed and private data sets. Based on the data partition pattern, FL is ofte…

eess.SP2020★ 23 cited

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

Haoran Sun, Wenqiang Pu, Minghe Zhu +3

There has been a growing interest in developing data-driven and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such a…

cs.IT2020★ 5 cited

Learning to Beamform in Heterogeneous Massive MIMO Networks

Minghe Zhu, Tsung-Hui Chang, Mingyi Hong

It is well-known that the problem of finding the optimal beamformers in massive multiple-input multiple-output (MIMO) networks is challenging because of its non-convexity, and conv…

math.OC2020★ 1 cited

First-Order Algorithms Without Lipschitz Gradient: A Sequential Local Optimization Approach

Junyu Zhang, Mingyi Hong

First-order algorithms have been popular for solving convex and non-convex optimization problems. A key assumption for the majority of these algorithms is that the gradient of the…

cs.CR2020

Imitation Privacy

Xun Xian, Xinran Wang, Mingyi Hong +2

In recent years, there have been many cloud-based machine learning services, where well-trained models are provided to users on a pay-per-query scheme through a prediction API. The…

eess.SP2020★ 2 cited

Joint Channel Assignment and Power Allocation for Multi-UAV Communication

Lingyun Zhou, Xihan Chen, Mingyi Hong +2

Unmanned aerial vehicle (UAV) swarm has emerged as a promising novel paradigm to achieve better coverage and higher capacity for future wireless network by exploiting the more favo…