在量子电路中找到精简版高效子模型，提升训练效率。
Investigating the Lottery Ticket Hypothesis for Variational Quantum Circuits
- 从大量子电路中挖掘出仅26%参数的高效子电路。
- 二值量子电路中仅用45%权重即达100%准确率。
- 为缓解量子优化困境提供新思路，适合量子机器学习研究者。
量子计算是计算机科学中快速发展的领域，尤其在机器学习方面取得显著进展。利用量子物理原理，其可突破经典算法局限。然而，依赖可调参数的变分量子电路（VQCs）常面临荒漠化平原现象，阻碍优化。彩票赢家假说（LTH）是经典机器学习中的新概念，可显著提升神经网络的参数效率：大型网络中存在更小、高效的子网络（‘赢家票’），性能相当，可能规避平原问题。本文探究该思想是否适用于VQCs。结果显示，弱LTH在VQCs中成立，发现的赢家票仅保留原参数的26.0%；对于强LTH（无训练直接学习剪枝掩码），在二值VQC中发现一个赢家票，在仅使用45%权重下实现100%准确率。这些结果表明，通过减少参数量，LTH或可缓解荒漠化平原问题，同时保持性能，从而提升量子机器学习任务中VQCs的效率。
原文摘要 · Abstract (English)
Quantum computing is an emerging field in computer science that has seen considerable progress in recent years, especially in machine learning. By harnessing the principles of quantum physics, it can surpass the limitations of classical algorithms. However, variational quantum circuits (VQCs), which rely on adjustable parameters, often face the barren plateau phenomenon, hindering optimization. The Lottery Ticket Hypothesis (LTH) is a recent concept in classical machine learning that has led to notable improvements in parameter efficiency for neural networks. It states that within a large network, a smaller, more efficient subnetwork, or ''winning ticket,'' can achieve comparable performance, potentially circumventing plateau challenges. In this work, we investigate whether this idea can apply to VQCs. We show that the weak LTH holds for VQCs, revealing winning tickets that retain just 26.0\% of the original parameters. For the strong LTH, where a pruning mask is learned without any training, we discovered a winning ticket in a binary VQC, achieving 100\% accuracy with only 45\% of the weights. These findings indicate that LTH may mitigate barren plateaus by reducing parameter counts while preserving performance, thus enhancing the efficiency of VQCs in quantum machine learning tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。