让数据主人在云端训练量子模型，无需上传数据也不需量子设备。
Training quantum machine learning models on cloud without uploading the data
- 先运行参数化量子电路，再编码数据，保护隐私
- 将电路深度从指数级降到线性，节省量子计算时间
- 训练后模型可纯用经典计算机运行，适合无量子硬件者
基于量子酉操作的线性特性，我们提出一种方法：在输入数据编码前先运行参数化量子电路。这使得数据所有者可在量子云平台上训练机器学习模型，而无需泄露数据信息。后续可通过经典计算高效编码大量数据，减少量子设备运行时间。训练完成的量子机器学习模型可完全在经典计算机上运行，数据所有者无需拥有任何量子硬件或量子模拟器。此外，该方法将编码所需电路深度从 $O(2^{n})$ 降低至 $O(n)$，并放宽了对量子门精度的要求。这些结果展示了量子及量子启发式机器学习模型相对于传统经典神经网络的又一优势，并拓展了数据安全的实现路径。
原文摘要 · Abstract (English)
Based on the linearity of quantum unitary operations, we propose a method that runs the parameterized quantum circuits before encoding the input data. This enables a dataset owner to train machine learning models on quantum cloud computation platforms, without the risk of leaking the information about the data. It is also capable of encoding a vast amount of data effectively at a later time using classical computations, thus saving runtime on quantum computation devices. The trained quantum machine learning models can be run completely on classical computers, meaning the dataset owner does not need to have any quantum hardware, nor even quantum simulators. Moreover, our method mitigates the encoding bottleneck by reducing the required circuit depth from $O(2^{n})$ to $O(n)$, and relax the tolerance on the precision of the quantum gates for the encoding. These results demonstrate yet another advantage of quantum and quantum-inspired machine learning models over existing classical neural networks, and broaden the approaches to data security.
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。