Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we called dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed.
翻译:为量子神经网络(QNNs)提议了若干结构,目的是高效率地完成量子数据方面的机器学习任务。对于特定量子神经网络的建设,迫切需要严格的缩放结果,以便了解哪些工程(如果有的话)可以大规模地培训。在这里,我们分析了我们最近提议的一个称为“消散的QNN(DQN)”的建筑的梯度(因而也是可培训性),我们称之为“消散的QNN(DQN)”的架构,每个层的输入量方位被该层的输出所丢弃。我们发现,DQNNs可以展示出不毛的高原,即在qubit数量中迅速消失的梯度。此外,我们提供了不同条件下DQNNs在不同的条件下的梯度(例如不同的成本功能和电路深度)的定量界限,并表明培训能力并非总能得到保证。