Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Doostmohammadian, Mohammadreza, Qureshi, Muhammad I., Khalesi, Mohammad Hossein, Rabiee, Hamid R., Khan, Usman A.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910779230388224
author Doostmohammadian, Mohammadreza
Qureshi, Muhammad I.
Khalesi, Mohammad Hossein
Rabiee, Hamid R.
Khan, Usman A.
author_facet Doostmohammadian, Mohammadreza
Qureshi, Muhammad I.
Khalesi, Mohammad Hossein
Rabiee, Hamid R.
Khan, Usman A.
contents Decentralized strategies are of interest for learning from large-scale data over networks. This paper studies learning over a network of geographically distributed nodes/agents subject to quantization. Each node possesses a private local cost function, collectively contributing to a global cost function, which the considered methodology aims to minimize. In contrast to many existing papers, the information exchange among nodes is log-quantized to address limited network-bandwidth in practical situations. We consider a first-order computationally efficient distributed optimization algorithm (with no extra inner consensus loop) that leverages node-level gradient correction based on local data and network-level gradient aggregation only over nearby nodes. This method only requires balanced networks with no need for stochastic weight design. It can handle log-scale quantized data exchange over possibly time-varying and switching network setups. We study convergence over both structured networks (for example, training over data-centers) and ad-hoc multi-agent networks (for example, training over dynamic robotic networks). Through experimental validation, we show that (i) structured networks generally result in a smaller optimality gap, and (ii) log-scale quantization leads to a smaller optimality gap compared to uniform quantization.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data
Doostmohammadian, Mohammadreza
Qureshi, Muhammad I.
Khalesi, Mohammad Hossein
Rabiee, Hamid R.
Khan, Usman A.
Systems and Control
Signal Processing
Optimization and Control
Decentralized strategies are of interest for learning from large-scale data over networks. This paper studies learning over a network of geographically distributed nodes/agents subject to quantization. Each node possesses a private local cost function, collectively contributing to a global cost function, which the considered methodology aims to minimize. In contrast to many existing papers, the information exchange among nodes is log-quantized to address limited network-bandwidth in practical situations. We consider a first-order computationally efficient distributed optimization algorithm (with no extra inner consensus loop) that leverages node-level gradient correction based on local data and network-level gradient aggregation only over nearby nodes. This method only requires balanced networks with no need for stochastic weight design. It can handle log-scale quantized data exchange over possibly time-varying and switching network setups. We study convergence over both structured networks (for example, training over data-centers) and ad-hoc multi-agent networks (for example, training over dynamic robotic networks). Through experimental validation, we show that (i) structured networks generally result in a smaller optimality gap, and (ii) log-scale quantization leads to a smaller optimality gap compared to uniform quantization.
title Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data
topic Systems and Control
Signal Processing
Optimization and Control
url https://arxiv.org/abs/2406.00621