Accelerating Inference for Multilayer Neural Networks with Quantum Computers

• URL: http://arxiv.org/abs/2510.07195v1
• Date: Wed, 08 Oct 2025 16:26:50 GMT
• Title: Accelerating Inference for Multilayer Neural Networks with Quantum Computers
• Authors: Arthur G. Rattew, Po-Wei Huang, Naixu Guo, Lirandë Pira, Patrick Rebentrost,
• Abstract summary: We present the first fully-coherent quantum implementation of a multilayer neural network with non-linear activation functions.<n>We analyse the complexity of inference for networks under three quantum data access regimes.
• Score: 4.168548169504036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $\epsilon$ with $O(\text{polylog}(N/\epsilon)^k)$ inference cost.

Related papers

• Dissipation-driven quantum generative adversarial networks [11.833077116494929]
  We introduce a novel dissipation-driven quantum generative adversarial network (DQGAN) architecture specifically tailored for generating classical data. The classical data is encoded into the input qubits of the input layer via strong tailored dissipation processes. We extract both the generated data and the classification results by measuring the observables of the steady state of the output qubits.
  arXiv  Detail & Related papers  (2024-08-28T07:41:58Z)
• SWAP-less Implementation of Quantum Algorithms [0.0]
  We present a formalism based on tracking the flow of parity quantum information to implement algorithms on devices with limited connectivity. We leverage the fact that entangling gates not only manipulate quantum states but can also be exploited to transport quantum information.
  arXiv  Detail & Related papers  (2024-08-20T14:51:00Z)
• Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients [51.82488018573326]
  We present QP-SBGD, a novel layer-wise optimiser tailored towards training neural networks with binary weights. BNNs reduce the computational requirements and energy consumption of deep learning models with minimal loss in accuracy. Our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware.
  arXiv  Detail & Related papers  (2023-10-23T17:32:38Z)
• Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation [8.947825738917869]
  Ridgelet transform has been a fundamental mathematical tool in the theoretical studies of neural networks. We develop a quantum ridgelet transform (QRT) which implements the ridgelet transform of a quantum state within a linear runtime $exp(O(D))$ of quantum computation. As an application, we show that one can use QRT as a fundamental subroutine for QML to efficiently find a sparse trainable subnetwork of large shallow wide neural networks.
  arXiv  Detail & Related papers  (2023-01-27T19:00:00Z)
• Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm [58.720142291102135]
  We show that useful information can be extracted from the quantum-mechanical implementation of Harrow-Hassidim-Lloyd (HHL) This paper shows, however, that useful information can be extracted from the quantum-mechanical implementation of HHL, and used to reduce the complexity of finding the solution on the classical side.
  arXiv  Detail & Related papers  (2022-10-23T11:58:05Z)
• Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach [64.23331120621118]
  This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks. We introduce a related embedded network and show that the embedded network can be used to provide an $ell_infty$-norm box over-approximation of the reachable sets of the original network. We apply our algorithms to train implicit neural networks on the MNIST dataset and compare the robustness of our models with the models trained via existing approaches in the literature.
  arXiv  Detail & Related papers  (2022-08-08T03:13:24Z)
• Optimizing Tensor Network Contraction Using Reinforcement Learning [86.05566365115729]
  We propose a Reinforcement Learning (RL) approach combined with Graph Neural Networks (GNN) to address the contraction ordering problem. The problem is extremely challenging due to the huge search space, the heavy-tailed reward distribution, and the challenging credit assignment. We show how a carefully implemented RL-agent that uses a GNN as the basic policy construct can address these challenges.
  arXiv  Detail & Related papers  (2022-04-18T21:45:13Z)
• Completely Quantum Neural Networks [0.0]
  We describe how to embed and train a general neural network in a quantum annealer. We develop three crucial ingredients: the free parameters of the network, the approximation of the activation function, and reduction of binary higher-order ingredients into ones. We implement this for an elementary network and illustrate the advantages of quantum training: its consistency in finding the global minimum of the loss function and the fact that the network training converges in a single step.
  arXiv  Detail & Related papers  (2022-02-23T19:00:03Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• A quantum algorithm for training wide and deep classical neural networks [72.2614468437919]
  We show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We numerically demonstrate that the MNIST image dataset satisfies such conditions. We provide empirical evidence for $O(log n)$ training of a convolutional neural network with pooling.
  arXiv  Detail & Related papers  (2021-07-19T23:41:03Z)
• Quantum Annealing Formulation for Binary Neural Networks [40.99969857118534]
  In this work, we explore binary neural networks, which are lightweight yet powerful models typically intended for resource constrained devices. We devise a quadratic unconstrained binary optimization formulation for the training problem. While the problem is intractable, i.e., the cost to estimate the binary weights scales exponentially with network size, we show how the problem can be optimized directly on a quantum annealer.
  arXiv  Detail & Related papers  (2021-07-05T03:20:54Z)
• A Greedy Algorithm for Quantizing Neural Networks [4.683806391173103]
  We propose a new computationally efficient method for quantizing the weights of pre- trained neural networks. Our method deterministically quantizes layers in an iterative fashion with no complicated re-training required.
  arXiv  Detail & Related papers  (2020-10-29T22:53:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.