no code implementations • 11 Apr 2024 • Chengyu Xia, Danny H. K. Tsang, Vincent K. N. Lau
We propose a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) FL framework where we firstly propose a hierarchical sparse prior to promote a clustered sparse structure in the weight matrix.
no code implementations • 15 Feb 2024 • Tailin Zhou, Jiadong Yu, Jun Zhang, Danny H. K. Tsang
This paper investigates resource allocation to provide heterogeneous users with customized virtual reality (VR) services in a mobile edge computing (MEC) system.
no code implementations • 11 Dec 2023 • Xuan He, Danny H. K. Tsang, Yize Chen
In this paper, we propose a novel planning and operation model minimizing the system-level carbon emissions via sitting and operating geographically shiftable resources.
no code implementations • 29 Sep 2023 • Tailin Zhou, Jun Zhang, Danny H. K. Tsang
Empirically, reducing data heterogeneity makes the connectivity on different paths more similar, forming more low-error overlaps between client and global modes.
no code implementations • 15 May 2023 • Jiadong Yu, Ahmad Alhilal, Tailin Zhou, Pan Hui, Danny H. K. Tsang
In this paper, we tackle this desynchronization using a continual RL framework that facilitates the resource allocation dynamically for MEC-enabled VR content streaming.
no code implementations • 13 May 2023 • Tailin Zhou, Zehong Lin, Jun Zhang, Danny H. K. Tsang
Based on these findings from our loss landscape visualization and loss decomposition, we propose utilizing iterative moving averaging (IMA) on the global model at the late training phase to reduce its deviation from the expected minimum, while constraining client exploration to limit the maximum distance between the global and client models.
no code implementations • 21 Feb 2023 • Chengyu Xia, Danny H. K. Tsang, Vincent K. N. Lau
We derive an efficient Turbo-variational Bayesian inferencing (Turbo-VBI) algorithm to solve the resulting model compression problem with the proposed prior.
1 code implementation • 17 Nov 2022 • Tailin Zhou, Jun Zhang, Danny H. K. Tsang
This enables client models to be updated in a shared feature space with consistent classifiers during local training.
no code implementations • 16 Nov 2022 • Jiadong Yu, Ahmad Alhilal, Pan Hui, Danny H. K. Tsang
Multi-access edge computing (MEC) provides responsive services to the end users, ensuring an immersive and interactive Metaverse experience.
no code implementations • 9 Nov 2022 • Jiadong Yu, Ahmad Alhilal, Pan Hui, Danny H. K. Tsang
The Metaverse has emerged as the successor of the conventional mobile internet to change people's lifestyles.
no code implementations • 18 Oct 2022 • Wenjing Liu, Shanpu Shen, Danny H. K. Tsang, Ranjan K. Mallik, Ross Murch
Different from original ratio detectors that use the magnitude ratio of the signals between two Reader antennas, in our proposed approach, we utilize the complex ratio so that phase information is preserved and propose an accurate linear channel model approximation.
no code implementations • 20 Sep 2022 • Jiadong Yu, Yang Li, Xiaolan Liu, Bo Sun, Yuan Wu, Danny H. K. Tsang
In this paper, we investigate the joint offloading, communication and computation resource allocation for IRS-assisted NOMA MEC system.
no code implementations • 1 Sep 2022 • Wanteng Ma, Ying Cao, Danny H. K. Tsang, Dong Xia
This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially non-concave cumulative rewards, hard resource constraints, and a non-separable regularizer.
no code implementations • 1 Aug 2022 • Xiaolan Liu, Jiadong Yu, Yuanwei Liu, Yue Gao, Toktam Mahmoodi, Sangarapillai Lambotharan, Danny H. K. Tsang
In this paper, we conduct a comprehensive overview of recent advances in distributed intelligence in wireless networks under the umbrella of native-AI wireless networks, with a focus on the basic concepts of native-AI wireless networks, on the AI-enabled edge computing, on the design of distributed learning architectures for heterogeneous networks, on the communication-efficient technologies to support distributed learning, and on the AI-empowered end-to-end communications.
no code implementations • NeurIPS 2021 • Bo Sun, Russell Lee, Mohammad Hajiesmaili, Adam Wierman, Danny H. K. Tsang
This paper leverages machine-learned predictions to design competitive algorithms for online conversion problems with the goal of improving the competitive ratio when predictions are accurate (i. e., consistency), while also guaranteeing a worst-case competitive ratio regardless of the prediction quality (i. e., robustness).
no code implementations • 26 Jan 2021 • Ying Cao, Bo Sun, Danny H. K. Tsang
In addition, since worst-case scenarios rarely occur in practice, we devise an adaptive implementation of our algorithm to improve its average-case performance and validate its effectiveness via simulations.
Data Structures and Algorithms
no code implementations • 14 Sep 2020 • Wenjing Liu, Shanpu Shen, Danny H. K. Tsang, Ross Murch
To overcome this challenge, we propose the use of orthogonal space-time block codes (OSTBC) by incorporating multiple antennas at the Tag as well as at the Reader.