一种可扩展的离散量子生成对抗神经网络
Towards a scalable discrete quantum generative adversarial neural network
摘要:
我们介绍了一个完全量子生成的对抗网络,用于处理二进制数据。该架构结合了其他经典和量子机器学习模型中的几个功能,到目前为止还没有结合使用。特别是,我们将噪声重新上传的发电机,辅助量子比特的量子增强表现力,和发电机和量子电路之间的直接连接,避免了需要访问发电机的概率分布。我们表明,作为单独的组件,发电机和稳压器执行所需的。我们的经验表明,我们的模型的表达能力的合成数据,以及低能量状态的伊辛模型。我们的演示表明,该模型不仅能够再现离散的训练数据,而且还可能从它推广。
英文摘要:
We introduce a fully quantum generative adversarial network intended for use with binary data. The architecture incorporates several features found in other classical and quantum machine learning models, which up to this point had not been used in conjunction. In particular, we incorporate noise reuploading in the generator, auxiliary qubits in the discriminator to enhance expressivity, and a direct connection between the generator and discriminator circuits, obviating the need to access the generator's probability distribution. We show that, as separate components, the generator and discriminator perform as desired. We empirically demonstrate the expressive power of our model on both synthetic data as well as low energy states of an Ising model. Our demonstrations suggest that the model is not only capable of reproducing discrete training data, but also of potentially generalizing from it.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。