论文标题
基于耗散感染的量子神经网络的训练性
Trainability of Dissipative Perceptron-Based Quantum Neural Networks
论文作者
论文摘要
已经提出了一些用于量子神经网络（QNN）的架构，目的是有效地执行机器学习任务。迫切需要进行严格的缩放结果，以了解特定的QNN构建体以了解哪种（如果有的话）可以大规模训练。在这里，我们为最近提出的架构分析了梯度缩放（以及训练性），我们称之为耗散QNNS（DQNNS），其中每层的输入量值都在该图层的输出处丢弃。我们发现DQNNS可以表现出贫瘠的高原，即在量子数量中呈指数级消失的梯度。此外，我们在不同条件下（例如不同的成本功能和电路深度）的DQNN梯度的缩放量表上提供了定量界限，并表明并非总是可以保证可训练性。
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.
