Towards Fault-Tolerant Quantum Deep Learning: Designing and Analyzing Quantum ResNet and Transformer with Quantum Arithmetic and Linear Algebra Primitives

• URL: http://arxiv.org/abs/2402.18940v3
• Date: Fri, 18 Jul 2025 09:30:10 GMT
• Title: Towards Fault-Tolerant Quantum Deep Learning: Designing and Analyzing Quantum ResNet and Transformer with Quantum Arithmetic and Linear Algebra Primitives
• Authors: Xiao-Fan Xu, Cheng Xue, Xi-Ning Zhuang, Yun-Jie Wang, Tai-Ping Sun, Yu Fang, Jun-Chao Wang, Huan-Yu Liu, Yu-Chun Wu, Zhao-Yun Chen, Guo-Ping Guo,
• Abstract summary: We introduce a framework to overcome the dual challenges of constructing deep architectures and the prohibitive overhead of data loading and measurement.<n>Our framework enables the design of multi-layer Quantum ResNet and Quantum Transformer models.<n>A cornerstone of our approach is a novel data transfer protocol, Discrete Chebyshev Decomposition (DCD), which facilitates this modularity.
• Score: 5.89456905230997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Achieving a practical quantum speedup for deep neural networks (DNNs) remains a central yet elusive goal, hindered by the dual challenges of constructing deep architectures and the prohibitive overhead of data loading and measurement. We introduce a framework to overcome these barriers, specifically targeting an asymptotic speedup with respect to the large input dimensions of modern DNNs (e.g., sequence length or image size). Our framework enables the design of multi-layer Quantum ResNet and Quantum Transformer models by strategically decomposing tasks: computationally intensive operations on the large input dimension are assigned to quantum linear algebra subroutines, while operations on the smaller, fixed feature dimension are handled by efficient quantum arithmetic. A cornerstone of our approach is a novel data transfer protocol, Discrete Chebyshev Decomposition (DCD), which facilitates this modularity. Numerical validation reveals a pivotal insight: the measurement cost required to maintain a target accuracy scales sublinearly with the input dimension. This sublinear scaling is the key to preserving the quantum advantage, ensuring that I/O overhead does not nullify the computational gains. A rigorous resource analysis further corroborates the superiority of our models in both efficiency and flexibility. Powered by this targeted acceleration strategy and the efficiency of DCD, our framework establishes a viable path toward scalable quantum deep learning.

Related papers

• Neural Network Architectures for Scalable Quantum State Tomography: Benchmarking and Memristor-Based Acceleration [0.9572566550427288]
  Quantum State Tomography (QST) is essential for characterizing and validating quantum systems.<n>Prior claims of performance have relied on architectural assumptions rather than systematic validation.<n>We benchmark several neural network architectures to determine which scale effectively with qubit number and which fail to maintain high fidelity as system size increases.
  arXiv  Detail & Related papers  (2025-07-30T18:12:10Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [60.996803677584424]
  Variational Quantum Circuits (VQCs) offer a novel pathway for quantum machine learning.<n>Their practical application is hindered by inherent limitations such as constrained linear expressivity, optimization challenges, and acute sensitivity to quantum hardware noise.<n>This work introduces VQC-MLPNet, a scalable and robust hybrid quantum-classical architecture designed to overcome these obstacles.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Hamiltonian Dynamics Learning: A Scalable Approach to Quantum Process Characterization [6.741097425426473]
  We introduce an efficient quantum process learning method specifically designed for short-time Hamiltonian dynamics. We demonstrate applications in quantum machine learning, where our protocol enables efficient training of variational quantum neural networks by directly learning unitary transformations. This work establishes a new theoretical foundation for practical quantum dynamics learning, paving the way for scalable quantum process characterization in both near-term and fault-tolerant quantum computing.
  arXiv  Detail & Related papers  (2025-03-31T14:50:00Z)
• The Impact of Architecture and Cost Function on Dissipative Quantum Neural Networks [0.016385815610837167]
  We present a novel architecture for dissipative quantum neural networks (DQNNs) in which each building block can implement any quantum channel.<n>We derive a versatile one-to-one parametrization of isometries, allowing for an efficient implementation of the proposed structure.
  arXiv  Detail & Related papers  (2025-02-13T17:38:48Z)
• Comprehensive Survey of QML: From Data Analysis to Algorithmic Advancements [2.5686697584463025]
  Quantum Machine Learning represents a paradigm shift at the intersection of Quantum Computing and Machine Learning. The field faces significant challenges, including hardware constraints, noise, and limited qubit coherence. This survey aims to provide a foundational resource for advancing Quantum Machine Learning toward practical, real-world applications.
  arXiv  Detail & Related papers  (2025-01-16T13:25:49Z)
• Quantum Pointwise Convolution: A Flexible and Scalable Approach for Neural Network Enhancement [0.0]
  We propose a novel architecture, which incorporates pointwise convolution within a quantum neural network framework.<n>By using quantum circuits, we map data to a higher-dimensional space, capturing more complex feature relationships.<n>In experiments, we applied the quantum pointwise convolution layer to classification tasks on the FashionMNIST and CIFAR10 datasets.
  arXiv  Detail & Related papers  (2024-12-02T08:03:59Z)
• QCircuitNet: A Large-Scale Hierarchical Dataset for Quantum Algorithm Design [17.747641494506087]
  We introduce QCircuitNet, the first benchmark and test dataset designed to evaluate AI's capability in designing and implementing quantum algorithms. Unlike using AI for writing traditional codes, this task is fundamentally different and significantly more complicated due to highly flexible design space and intricate manipulation of qubits.
  arXiv  Detail & Related papers  (2024-10-10T14:24:30Z)
• Application of Large Language Models to Quantum State Simulation [0.11666234644810894]
  Currently, various quantum simulators provide powerful tools for researchers, but simulating quantum evolution with these simulators often incurs high time costs. This paper details the process of constructing 1-qubit and 2-qubit quantum simulator models, extending to multiple qubits, and ultimately implementing a 3-qubit example. Our study demonstrates that LLMs can effectively learn and predict the evolution patterns among quantum bits, with minimal error compared to the theoretical output states.
  arXiv  Detail & Related papers  (2024-10-09T07:23:13Z)
• Shedding Light on the Future: Exploring Quantum Neural Networks through Optics [3.1935899800030096]
  Quantum neural networks (QNNs) play an important role as an emerging technology in the rapidly developing field of quantum machine learning. This article reviews the concept of QNNs and their physical realizations, particularly implementations based on quantum optics.
  arXiv  Detail & Related papers  (2024-09-04T08:49:57Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures [1.8781124875646162]
  This research contributes to the advancement of scalable quantum computing systems by introducing a novel learning-based approach for efficient quantum circuit compilation and mapping. In this work, we propose a novel approach employing Deep Reinforcement Learning (DRL) methods to learn theses for a specific multi-core architecture.
  arXiv  Detail & Related papers  (2024-06-17T12:09:11Z)
• Quantum Generative Adversarial Networks: Bridging Classical and Quantum Realms [0.6827423171182153]
  We explore the synergistic fusion of classical and quantum computing paradigms within the realm of Generative Adversarial Networks (GANs) Our objective is to seamlessly integrate quantum computational elements into the conventional GAN architecture, thereby unlocking novel pathways for enhanced training processes. This research is positioned at the forefront of quantum-enhanced machine learning, presenting a critical stride towards harnessing the computational power of quantum systems.
  arXiv  Detail & Related papers  (2023-12-15T16:51:36Z)
• Near-Term Distributed Quantum Computation using Mean-Field Corrections and Auxiliary Qubits [77.04894470683776]
  We propose near-term distributed quantum computing that involve limited information transfer and conservative entanglement production. We build upon these concepts to produce an approximate circuit-cutting technique for the fragmented pre-training of variational quantum algorithms.
  arXiv  Detail & Related papers  (2023-09-11T18:00:00Z)
• Entanglement-Assisted Quantum Networks: Mechanics, Enabling Technologies, Challenges, and Research Directions [66.27337498864556]
  This paper presents a comprehensive survey of entanglement-assisted quantum networks. It provides a detailed overview of the network structure, working principles, and development stages. It also emphasizes open research directions, including architecture design, entanglement-based network issues, and standardization.
  arXiv  Detail & Related papers  (2023-07-24T02:48:22Z)
• Quantum Neural Architecture Search with Quantum Circuits Metric and Bayesian Optimization [2.20200533591633]
  We propose a new quantum gates distance that characterizes the gates' action over every quantum state. Our approach significantly outperforms the benchmark on three empirical quantum machine learning problems.
  arXiv  Detail & Related papers  (2022-06-28T16:23:24Z)
• 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)
• 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)
• On exploring the potential of quantum auto-encoder for learning quantum systems [60.909817434753315]
  We devise three effective QAE-based learning protocols to address three classically computational hard learning problems. Our work sheds new light on developing advanced quantum learning algorithms to accomplish hard quantum physics and quantum information processing tasks.
  arXiv  Detail & Related papers  (2021-06-29T14:01:40Z)
• Fast Swapping in a Quantum Multiplier Modelled as a Queuing Network [64.1951227380212]
  We propose that quantum circuits can be modeled as queuing networks. Our method is scalable and has the potential speed and precision necessary for large scale quantum circuit compilation.
  arXiv  Detail & Related papers  (2021-06-26T10:55:52Z)
• Quantum-tailored machine-learning characterization of a superconducting qubit [50.591267188664666]
  We develop an approach to characterize the dynamics of a quantum device and learn device parameters. This approach outperforms physics-agnostic recurrent neural networks trained on numerically generated and experimental data. This demonstration shows how leveraging domain knowledge improves the accuracy and efficiency of this characterization task.
  arXiv  Detail & Related papers  (2021-06-24T15:58:57Z)
• Tensor Network Quantum Virtual Machine for Simulating Quantum Circuits at Exascale [57.84751206630535]
  We present a modernized version of the Quantum Virtual Machine (TNQVM) which serves as a quantum circuit simulation backend in the e-scale ACCelerator (XACC) framework. The new version is based on the general purpose, scalable network processing library, ExaTN, and provides multiple quantum circuit simulators. By combining the portable XACC quantum processors and the scalable ExaTN backend we introduce an end-to-end virtual development environment which can scale from laptops to future exascale platforms.
  arXiv  Detail & Related papers  (2021-04-21T13:26:42Z)
• The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning [84.33745072274942]
  We show how to represent linear and non-linear layers as unitary quantum gates, and interpret the fundamental excitations of the quantum model as particles. On top of opening a new perspective and techniques for studying neural networks, the quantum formulation is well suited for optical quantum computing.
  arXiv  Detail & Related papers  (2021-03-08T17:24:29Z)
• Experimental Quantum Generative Adversarial Networks for Image Generation [93.06926114985761]
  We experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor. Our work provides guidance for developing advanced quantum generative models on near-term quantum devices.
  arXiv  Detail & Related papers  (2020-10-13T06:57:17Z)

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.