Accelerating Inference for Multilayer Neural Networks with Quantum Computers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rattew, Arthur G., Huang, Po-Wei, Guo, Naixu, Pira, Lirandë, Rebentrost, Patrick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911691302764544
author Rattew, Arthur G.
Huang, Po-Wei
Guo, Naixu
Pira, Lirandë
Rebentrost, Patrick
author_facet Rattew, Arthur G.
Huang, Po-Wei
Guo, Naixu
Pira, Lirandë
Rebentrost, Patrick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07195
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerating Inference for Multilayer Neural Networks with Quantum Computers
Rattew, Arthur G.
Huang, Po-Wei
Guo, Naixu
Pira, Lirandë
Rebentrost, Patrick
Quantum Physics
Machine Learning
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.
title Accelerating Inference for Multilayer Neural Networks with Quantum Computers
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2510.07195