Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn?

Forum topic · 小凯 · 2026-10-20

Summary

This arXiv paper (2610.23827) by Anis Bekri, Amar Abane, Van Sy Mai, Abdella Battou, and Saddek Bensalem examines how future quantum networks should estimate end-to-end entanglement quality for control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Inspired by quality-of-transmission (QoT) estimation in optical networks, the authors propose a framework for deciding when a quantum controller should compute fidelity analytically, simulate it, or learn a surrogate model. The optical analogy is useful but incomplete: unlike scalar transmission margins in optical networks, quantum QoT estimation must account for probabilistic entanglement generation, random memory waiting times, decoherence, state consumption, and measurement constraints, making fidelity a stochastic target. A simulation-based proof of concept shows that analytical composition suffices in simple cases, simulation is necessary when stochastic memory effects shape the delivered fidelity distribution, and lightweight learned surrogates can approximate simulator outputs at far lower runtime cost for online control. Open deployment challenges include stochastic targets, sim-to-real transfer, data generation cost, physics-informed learning, and generalization from single paths to network-wide topologies.

Paper Overview

Field: Machine Learning Authors: Anis Bekri, Amar Abane, Van Sy Mai, Abdella Battou, Saddek Bensalem Published: 2026-10-16 arXiv: 2610.23827

Abstract (Original)

Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision depends on a timely and reliable estimate of the quality of the entanglement that a candidate path can deliver, with end-to-end fidelity as a central metric. Inspired by the optical-networking experience with quality-of-transmission (QoT) estimation, this article asks when a quantum controller should compute fidelity analytically, simulate it, or learn a surrogate model. The optical analogy is useful but incomplete: optical QoT estimation often predicts a scalar transmission margin, whereas quantum QoT estimation must account for probabilistic entanglement generation, random memory waiting times, decoherence, state consumption, and measurement constraints, which make fidelity a stochastic target.

Key Points

Proposes a compute / simulate / learn framework for quantum quality-of-transmission (QoT) estimation, illustrated with a simulation-based proof of concept.
Analytical composition is sufficient for simple scenarios.
Simulation becomes necessary when stochastic memory effects shape the distribution of delivered fidelity.
Lightweight learned surrogates can approximate simulator labels, offering much lower runtime cost for online control-plane decisions.
The optical-networking QoT analogy is useful but incomplete: quantum fidelity is a stochastic target shaped by probabilistic entanglement generation, random memory waiting times, decoherence, state consumption, and measurement constraints.

Open Challenges

The paper concludes by discussing deployment challenges, including:

Handling stochastic fidelity targets
Simulation-to-reality (sim-to-real) transfer
Cost of data generation for training
Physics-informed learning
Generalization from single-path estimation to network-wide topologies

--- *Auto-collected on 2026-10-20*