Search Results for author: Jingyang Zhu

Found 4 papers, 0 papers with code

Over-the-Air Federated Learning and Optimization

no code implementations16 Oct 2023 Jingyang Zhu, Yuanming Shi, Yong Zhou, Chunxiao Jiang, Wei Chen, Khaled B. Letaief

We first provide a comprehensive study on the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both strongly convex and non-convex settings with constant and diminishing learning rates in the presence of data heterogeneity.

Federated Learning

Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation

no code implementations3 Apr 2021 Xizi Chen, Jingyang Zhu, Jingbo Jiang, Chi-Ying Tsui

Through permutation, the optimal arrangement of the weight matrix is obtained, and the sparse weight matrix is further compressed to a small and dense format to make full use of the hardware resources.

Model Compression

Fast Convergence Algorithm for Analog Federated Learning

no code implementations30 Oct 2020 Shuhao Xia, Jingyang Zhu, Yuhan Yang, Yong Zhou, Yuanming Shi, Wei Chen

In this paper, we consider federated learning (FL) over a noisy fading multiple access channel (MAC), where an edge server aggregates the local models transmitted by multiple end devices through over-the-air computation (AirComp).

Federated Learning

SparseNN: An Energy-Efficient Neural Network Accelerator Exploiting Input and Output Sparsity

no code implementations3 Nov 2017 Jingyang Zhu, Jingbo Jiang, Xizi Chen, Chi-Ying Tsui

Furthermore, an energy-efficient hardware architecture, SparseNN, is proposed to exploit both the input and output sparsity.

Efficient Neural Network

Cannot find the paper you are looking for? You can Submit a new open access paper.