Robust Asynchronous and Network-Independent Cooperative Learning

10/20/2020
by   Eduardo Mojica-Nava, et al.
0

We consider the model of cooperative learning via distributed non-Bayesian learning, where a network of agents tries to jointly agree on a hypothesis that best described a sequence of locally available observations. Building upon recently proposed weak communication network models, we propose a robust cooperative learning rule that allows asynchronous communications, message delays, unpredictable message losses, and directed communication among nodes. We show that our proposed learning dynamics guarantee that all agents in the network will have an asymptotic exponential decay of their beliefs on the wrong hypothesis, indicating that the beliefs of all agents will concentrate on the optimal hypotheses. Numerical experiments provide evidence on a number of network setups.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2021

Communication-Efficient Distributed Cooperative Learning with Compressed Beliefs

We study the problem of distributed cooperative learning, where a group ...
research
11/16/2022

Asynchronous Bayesian Learning over a Network

We present a practical asynchronous data fusion model for networked agen...
research
05/06/2016

Distributed Learning with Infinitely Many Hypotheses

We consider a distributed learning setup where a network of agents seque...
research
04/10/2017

Distributed Learning for Cooperative Inference

We study the problem of cooperative inference where a group of agents in...
research
10/25/2021

Self-aware Social Learning over Graphs

In this paper we study the problem of social learning under multiple tru...
research
11/20/2020

A General Framework for Distributed Inference with Uncertain Models

This paper studies the problem of distributed classification with a netw...
research
05/27/2011

AntNet: Distributed Stigmergetic Control for Communications Networks

This paper introduces AntNet, a novel approach to the adaptive learning ...

Please sign up or login with your details

Forgot password? Click here to reset