Quantum neural networks (QNNs) have generated excitement around the possibility of efficiently analyzing quantum data. But this excitement has been tempered by the existence of exponentially vanishing gradients, known as barren plateau landscapes, for many QNN architectures. Recently, Quantum Convolutional Neural Networks (QCNNs) have been proposed, involving a sequence of convolutional and pooling layers that reduce the number of qubits while preserving information about relevant data features. In this work we rigorously analyze the gradient scaling for the parameters in the QCNN architecture. We find that the variance of the gradient vanishes no faster than polynomially, implying that QCNNs do not exhibit barren plateaus. This provides an analytical guarantee for the trainability of randomly initialized QCNNs, which highlights QCNNs as being trainable under random initialization unlike many other QNN architectures. To derive our results we introduce a novel graph-based method to analyze expectation values over Haar-distributed unitaries, which will likely be useful in other contexts. Finally, we perform numerical simulations to verify our analytical results.
翻译:量子神经网络(QNNs)在有效分析量子数据的可能性方面引起了兴奋。但这种兴奋因许多QNN的建筑存在指数性消失的梯度(称为贫瘠高原景观)而减弱。最近,提出了“量子革命神经网络(QCNNs)”建议,涉及一系列变动和集合层,以减少qubits数量,同时保存有关数据特征的信息。在这项工作中,我们严格分析QCNN结构参数的梯度缩放。我们发现,梯度的差异不会以多元方式更快地消失,这意味着QCNNs不会出现贫瘠高地。这为随机初始化的QCNNs的训练提供了分析保证,这突出表明,QCNNs可以在随机初始化的情况下接受培训,而不像其他许多QNN结构。为了得出我们的成果,我们采用了一种新的基于图表的方法来分析Haar派单位的预期值,这在其他情况下可能有用。最后,我们进行了数字模拟,以核实我们的分析结果。