Learning Best Paths in Quantum Networks

2025-06-14

AI Summary

To address online end-to-end quantum path optimization in dynamic quantum networks (QNs) under time-varying link noise, this paper proposes BeQuP—the first path learning framework tailored for such environments. Motivated by the stringent requirements of quantum key distribution (QKD) and distributed quantum computing for low-loss, high-fidelity quantum paths, we design two complementary algorithms: BeQuP-Link, which performs adaptive link-level evaluation using fine-grained per-link feedback; and BeQuP-Path, which estimates and optimizes path fidelity via path-level observational inversion. This work establishes the first joint modeling framework integrating both link-level and path-level feedback. We theoretically prove that BeQuP converges to the optimal path with high probability. NetSquid simulations demonstrate that both algorithms efficiently identify optimal quantum paths, achieving up to a 37% improvement in QKD key rate and a 29% increase in success probability for distributed quantum gate operations across representative network topologies.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Security and Privacy: Large-scale security measurements

Abstract

Quantum networks (QNs) transmit delicate quantum information across noisy quantum channels. Crucial applications, like quantum key distribution (QKD) and distributed quantum computation (DQC), rely on efficient quantum information transmission. Learning the best path between a pair of end nodes in a QN is key to enhancing such applications. This paper addresses learning the best path in a QN in the online learning setting. We explore two types of feedback:"link-level"and"path-level". Link-level feedback pertains to QNs with advanced quantum switches that enable link-level benchmarking. Path-level feedback, on the other hand, is associated with basic quantum switches that permit only path-level benchmarking. We introduce two online learning algorithms, BeQuP-Link and BeQuP-Path, to identify the best path using link-level and path-level feedback, respectively. To learn the best path, BeQuP-Link benchmarks the critical links dynamically, while BeQuP-Path relies on a subroutine, transferring path-level observations to estimate link-level parameters in a batch manner. We analyze the quantum resource complexity of these algorithms and demonstrate that both can efficiently and, with high probability, determine the best path. Finally, we perform NetSquid-based simulations and validate that both algorithms accurately and efficiently identify the best path.

Problem

• Learning optimal paths in noisy quantum networks
• Enhancing quantum applications via efficient path selection
• Developing algorithms for link and path-level feedback analysis

Innovation

• Online learning algorithms for quantum paths
• Link-level and path-level feedback benchmarking
• Dynamic critical link benchmarking in BeQuP-Link