Online Learning of Network Bottlenecks via Minimax Paths

TL;DR

This paper introduces an online learning approach for identifying network bottlenecks by estimating minimax paths in stochastic networks, using a combinatorial semi-bandit model and Thompson Sampling, with theoretical regret bounds and empirical validation.

Contribution

It develops a novel combinatorial semi-bandit framework for bottleneck detection in stochastic networks and proposes an efficient approximation method with theoretical and experimental validation.

Findings

Thompson Sampling achieves sublinear Bayesian regret bounds.

The approximation method performs well on real-world networks.

Empirical results validate the effectiveness of the proposed approach.

Abstract

In this paper, we study bottleneck identification in networks via extracting minimax paths. Many real-world networks have stochastic weights for which full knowledge is not available in advance. Therefore, we model this task as a combinatorial semi-bandit problem to which we apply a combinatorial version of Thompson Sampling and establish an upper bound on the corresponding Bayesian regret. Due to the computational intractability of the problem, we then devise an alternative problem formulation which approximates the original objective. Finally, we experimentally evaluate the performance of Thompson Sampling with the approximate formulation on real-world directed and undirected networks.