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
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/14/2021

Decentralized Riemannian Gradient Descent on the Stiefel Manifold

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

A Decentralized Approach to Bayesian Learning

Motivated by decentralized approaches to machine learning, we propose a ...
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...
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...
04/18/2022

On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks

We study the decentralized consensus and stochastic optimization problem...
04/06/2022

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

In this paper, we propose a new, simplified high probability analysis of...
11/04/2021

Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear Gossiping

Distributed learning has become an integral tool for scaling up machine ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.