Gradient and Projection Free Distributed Online Min-Max Resource Optimization

12/07/2021
by   Jingrong Wang, et al.
0

We consider distributed online min-max resource allocation with a set of parallel agents and a parameter server. Our goal is to minimize the pointwise maximum over a set of time-varying convex and decreasing cost functions, without a priori information about these functions. We propose a novel online algorithm, termed Distributed Online resource Re-Allocation (DORA), where non-stragglers learn to relinquish resource and share resource with stragglers. A notable feature of DORA is that it does not require gradient calculation or projection operation, unlike most existing online optimization strategies. This allows it to substantially reduce the computation overhead in large-scale and distributed networks. We show that the dynamic regret of the proposed algorithm is upper bounded by O(T^3/4(1+P_T)^1/4), where T is the total number of rounds and P_T is the path-length of the instantaneous minimizers. We further consider an application to the bandwidth allocation problem in distributed online machine learning. Our numerical study demonstrates the efficacy of the proposed solution and its performance advantage over gradient- and/or projection-based resource allocation algorithms in reducing wall-clock time.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2017

Improved Convergence Rates for Distributed Resource Allocation

In this paper, we develop a class of decentralized algorithms for solvin...
research
10/22/2020

Resource allocation for task-level speculative scientific applications: a proof of concept using Parallel Trajectory Splicing

The constant increase in parallelism available on large-scale distribute...
research
09/22/2019

Distributed Conjugate Gradient Tracking for Resource Allocation in Unbalanced Networks

This paper proposes a distributed conjugate gradient tracking algorithm ...
research
04/16/2021

Welfare Measure for Resource Allocation with Algorithmic Implementation: Beyond Average and Max-Min

In this work, we propose an axiomatic approach for measuring the perform...
research
08/18/2018

Optimization of LTE Radio Resource Block Allocation for Maritime Channels

In this study, we describe the behavior of LTE over the sea and investig...
research
09/04/2018

Multi-Path Alpha-Fair Resource Allocation at Scale in Distributed Software Defined Networks

The performance of computer networks relies on how bandwidth is shared a...
research
12/21/2018

Derandomized Distributed Multi-resource Allocation with Little Communication Overhead

We study a class of distributed optimization problems for multiple share...

Please sign up or login with your details

Forgot password? Click here to reset