Low complexity convergence rate bounds for the synchronous gossip subclass of push-sum algorithms

07/12/2023
by   Balázs Gerencsér, et al.
0

We develop easily accessible quantities for bounding the almost sure exponential convergence rate of push-sum algorithms. We analyze the scenario of i.i.d. synchronous gossip, every agent communicating towards its single target at every step. Multiple bounding expressions are developed depending on the generality of the setup, all functions of the spectrum of the network. While the most general bound awaits further improvement, with more symmetries, close bounds can be established, as demonstrated by numerical simulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/21/2020

On the limitations of single-step drift and minorization in Markov chain convergence analysis

Over the last three decades, there has been a considerable effort within...
research
03/23/2018

Asynchronous Subgradient-Push

We consider a multi-agent framework for distributed optimization where e...
research
02/01/2020

Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-Learning

We consider a general asynchronous Stochastic Approximation (SA) scheme ...
research
07/09/2020

Geometric Bounds for Convergence Rates of Averaging Algorithms

We develop a generic method for bounding the convergence rate of an aver...
research
01/31/2019

Tight bounds on the convergence rate of generalized ratio consensus algorithms

The problems discussed in this paper are motivated by the ratio consensu...
research
10/06/2021

Tight Bounds on the Optimal UL Sum-Rate of MU RIS-aided Wireless Systems

The objective of this paper is to develop simple techniques to bound the...
research
10/18/2016

Analysis and Implementation of an Asynchronous Optimization Algorithm for the Parameter Server

This paper presents an asynchronous incremental aggregated gradient algo...

Please sign up or login with your details

Forgot password? Click here to reset