首次实现带非线性激活的多层神经网络量子化，可加速深度学习推理。
Accelerating Inference for Multilayer Neural Networks with Quantum Computers
- 构建类ResNet的量子神经网络，含卷积、激活和跳跃连接
- 在理想条件下实现四倍于经典方法的推理加速
- 适合研究量子机器学习加速的学者与工程师
容错量子处理单元（QPUs）有望在特定计算任务中实现指数级加速，但其与现代深度学习流程的集成仍不明确。本文首次提出全相干的多层神经网络量子实现，包含非线性激活函数，结构仿照广泛使用的ResNet架构，包含多滤波二维卷积、Sigmoid激活、跳跃连接和层归一化。我们分析了三种量子数据访问模式下的推理复杂度：在无假设下，对浅层双线性网络实现二次加速；当权重可高效量子访问时，获得四次加速；当输入与权重均可高效量子访问时，证明一个具有N维向量化输入、k个残差块层及最终残差-线性-池化层的网络，可在误差ε下以O(polylog(N/ε)^k)的代价完成推理。
原文摘要 · Abstract (English)
Fault-tolerant Quantum Processing Units (QPUs) promise to deliver exponential speed-ups in select computational tasks, yet their integration into modern deep learning pipelines remains unclear. In this work, we take a step towards bridging this gap by presenting the first fully-coherent quantum implementation of a multilayer neural network with non-linear activation functions. Our constructions mirror widely used deep learning architectures based on ResNet, and consist of residual blocks with multi-filter 2D convolutions, sigmoid activations, skip-connections, and layer normalizations. We analyse the complexity of inference for networks under three quantum data access regimes. Without any assumptions, we establish a quadratic speedup over classical methods for shallow bilinear-style networks. With efficient quantum access to the weights, we obtain a quartic speedup over classical methods. With efficient quantum access to both the inputs and the network weights, we prove that a network with an $N$-dimensional vectorized input, $k$ residual block layers, and a final residual-linear-pooling layer can be implemented with an error of $ε$ with $O(\text{polylog}(N/ε)^k)$ inference cost.
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。