Department of Electrical & Computer Engineering UC Davis

NSF Funded MLWins Project Website

PI: Z. Ding (UC Davis), Junshang Zhang and Gautam Dararathy (ASU), Na Li (Harvard U.)

Visit PI Institutional Research Pages for more related works: Prof. Z. Ding

Collaborative Research: MLWiNS: Distributed Learning over Multi-Access Channels: From Bandlimited Coordinate Descent to Gradient Sketching
Project Overview

The past decade has witnessed an explosive growth of Internet of Things (IoT) services. An earlier report by Cisco predicted that the number of connected devices and subjects (including machines, humans, and things) can potentially grow to 500 billions by 2025. A general consensus is that much of IoT-created data will have to be stored and analyzed near, or at the network edge. This need has given rise to a new computing paradigm, namely edge computing, which features a new architecture by extending cloud computing to the network edge with low latency. Aiming to develop an integrated distributed learning and wireless networking framework, this project takes a principled approach to investigate two categories of edge learning algorithms tailored for wireless MAC channels, namely bandlimited coordinate descent and bandlimited gradient sketching. In these algorithms, sparsified or sketched versions of local updates are exchanged using multicarrier transmissions constrained by bandwidth; and each sender carries out power allocation across subcarriers based on gradient values and channel conditions through coordinated integration Furthermore, we devise edge learning algorithms using two intimately related methods: 1) first-order stochastic gradient descent methods and 2) zero-order stochastic optimization methods. In particular, zero-order methods are derivative-free so they are very promising for wireless edge learning.

Return to Research Pages for more related works:
UC Davis: Prof. Z. Ding
ASU Collaborators
Harvard University Collaborator

Research Task Synopsis
    The chief tasks of this collaborative project include:

  • Task 1: Bandlimited Coordinate Descent: Learning-driven Joint Power Allocation and Gradient Estimation.
  • Task 2: Bandlimited Gradient Sketching: Power Control and Bandwidth-Accuracy Tradeoffs.
  • Task 3: Bandlimited Coordinate Descent based on Zero-order Estimates.
  • Task 4: Bandlimited Gradient Sketching based on Zero-order Methods.
  • Task 5: Exploiting RF Characteristics in DL-Based CSI Estimation.
UC Davis Participants
  • PI: Z. Ding;

  • Researcher Team Membberss: Yu-Chien Lin, Songyang Zhang, Mason del Rosario

  • UC Davis Publications
    1. Lin, Yu-Chien and Liu, Zhenyu and Lee, Ta-Sung and Ding, Zhi (2021). Deep Learning Phase Compression for MIMO CSI Feedback by Exploiting FDD Channel Reciprocity. IEEE Wireless Communications Letters. 1 to 1. Published. 2162-2337.

    2. Zhang, Songyang and Cui, Shuguang and Ding, Zhi (2021). Hypergraph Spectral Analysis and Processing in 3D Point Cloud. 30. IEEE Transactions on Image Processing, 30. 1193 to 1206. Published. 1057-7149.

    3. Zhenyu Liu, Mason del (2021). A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI Feedback. IEEE Transactions on Wireless Communications. Published. 1558-2248.

    Collaborators' Publications
    1. Y. Tang, J. Zhang, and N. Li, ``Distributed zero-order algorithms for nonconvex multi-agent op-timization,'' IEEE Transactions on Control of Network Systems. 8 (1) 269 to 281, 2021.

    2. Malu, Mohit and Dasarathy, Gautam and Spanias, Andreas. ``Bayesian Optimization in High-Dimensional Spaces: A Brief Survey.'' International Conference on Information Intelligence Systems and Applications.

    3. Li, Weizhi and Dasarathy, Gautam and Ramamurthy, Karthikeyan N. and Berisha, Visar. ``Finding the Homology of Decision Boundaries with Active Learning.'' Advances in neural information processing systems 2020.

    4. J. Zhang, N. Li and M. Dedeoglu: ``Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach,'' presented at INFOCOM 2021.