Performance and Convergence of Multi-user Online Learning

TL;DR

This paper analyzes how decentralized multi-user online learning algorithms can achieve optimal channel allocations in wireless networks despite uncertainty and limited cooperation, highlighting the impact of knowledge and communication levels.

Contribution

It investigates conditions under which socially optimal allocations are achievable in decentralized multi-user online learning with varying cooperation and knowledge levels.

Findings

Lower cooperation reduces the likelihood of achieving social optimality.

Increased uncertainty about channel quality makes optimal allocation harder to attain.

The study provides conditions for convergence to optimal allocations under different information settings.

Abstract

We study the problem of allocating multiple users to a set of wireless channels in a decentralized manner when the channel quali- ties are time-varying and unknown to the users, and accessing the same channel by multiple users leads to reduced quality due to interference. In such a setting the users not only need to learn the inherent channel quality and at the same time the best allocations of users to channels so as to maximize the social welfare. Assuming that the users adopt a certain online learning algorithm, we investigate under what conditions the socially optimal allocation is achievable. In particular we examine the effect of different levels of knowledge the users may have and the amount of communications and cooperation. The general conclusion is that when the cooperation of users decreases and the uncertainty about channel payoffs increases it becomes harder to achieve the socially opti- mal allocation.