On the Convergence of Consensus Algorithms with Markovian Noise and Gradient Bias

08/18/2020
by   Hoi-To Wai, et al.
0

This paper presents a finite time convergence analysis for a decentralized stochastic approximation (SA) scheme. The scheme generalizes several algorithms for decentralized machine learning and multi-agent reinforcement learning. Our proof technique involves separating the iterates into their respective consensual parts and consensus error. The consensus error is bounded in terms of the stationarity of the consensual part, while the updates of the consensual part can be analyzed as a perturbed SA scheme. Under the Markovian noise and time varying communication graph assumptions, the decentralized SA scheme has an expected convergence rate of O(log T/ √(T) ), where T is the iteration number, in terms of squared norms of gradient for nonlinear SA with smooth but non-convex cost function. This rate is comparable to the best known performances of SA in a centralized setting with a non-convex potential function.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2021

Decentralized Riemannian Gradient Descent on the Stiefel Manifold

We consider a distributed non-convex optimization where a network of age...
research
07/14/2020

A Decentralized Approach to Bayesian Learning

Motivated by decentralized approaches to machine learning, we propose a ...
research
08/10/2020

An improved convergence analysis for decentralized online stochastic non-convex optimization

In this paper, we study decentralized online stochastic non-convex optim...
research
10/14/2022

Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization

Decentralized optimization is effective to save communication in large-s...
research
12/20/2021

Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks

In decentralized learning, a network of nodes cooperate to minimize an o...
research
10/27/2022

Decentralized Federated Learning via Non-Coherent Over-the-Air Consensus

This paper presents NCOTA-DGD, a Decentralized Gradient Descent (DGD) al...
research
06/17/2019

On linear convergence of two decentralized algorithms

Decentralized algorithms solve multi-agent problems over a connected net...

Please sign up or login with your details

Forgot password? Click here to reset