Quantitative Evaluation of Quantum/Classical Neural Network Using a Game Solver Metric

2025-03-27

AI Summary

This work addresses the challenges of quantum computing system performance evaluation and quantum advantage verification by proposing an Elo-rating-based benchmark framework grounded in automated tic-tac-toe gameplay. Methodologically, we implement and compare classical convolutional neural networks (CNNs), quantum convolutional neural networks (QCNNs), and quantum-classical hybrid models under realistic noisy quantum channels, while explicitly quantifying the overhead introduced by quantum communication. Our contributions are twofold: (1) We introduce the Elo rating system to quantum-classical neural network comparison for the first time, enabling reproducible and scalable cross-paradigm performance assessment; (2) We systematically characterize the practical quantum communication overhead in QCNN deployment—demonstrating its negligible impact, with hybrid models achieving Elo scores comparable to classical CNNs, whereas purely quantum models suffer significant degradation due to hardware noise. Results validate both the benchmark’s effectiveness and the practical promise of hybrid architectures.

Technology Category

• Machine Learning: Quantum Machine Learning
• Game Theory and Economic Paradigms: Adversarial Learning
• Multiagent Systems: Adversarial Agents

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

To evaluate the performance of quantum computing systems relative to classical counterparts and explore the potential for quantum advantage, we propose a game-solving benchmark based on Elo ratings in the game of tic-tac-toe. We compare classical convolutional neural networks (CNNs), quantum convolutional neural networks (QCNNs), and hybrid classical-quantum models by assessing their performance against a random-move agent in automated matches. Additionally, we implement a QCNN integrated with quantum communication and evaluate its performance to quantify the overhead introduced by noisy quantum channels. Our results show that the classical-quantum hybrid model achieves Elo ratings comparable to those of classical CNNs, while the standalone QCNN underperforms under current hardware constraints. The communication overhead was found to be modest. These findings demonstrate the viability of using game-based benchmarks for evaluating quantum computing systems and suggest that quantum communication can be incorporated with limited impact on performance, providing a foundation for future hybrid quantum applications.

Problem

• Evaluating quantum vs classical neural networks using game benchmarks
• Assessing performance of hybrid quantum-classical models in tic-tac-toe
• Quantifying quantum communication overhead in noisy channels

Innovation

• Game-solving benchmark using Elo ratings
• Hybrid classical-quantum neural network model
• Quantum communication with modest overhead