Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2605.13979

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

Natsuto Isogai, Hayata Yamasaki, Sho Sonoda, Mio Murao

quant-phcs.LGstat.MLSubmitted May 13, 2026• Announced May 15, 2026• 1 citation
arXivHTMLPDF

Abstract

Quantum machine learning (QML) aims to accelerate machine learning tasks by exploiting quantum computation. Previous work studied a QML algorithm for selecting sparse subnetworks from large shallow neural networks. Instead of directly solving an optimization problem over a large-scale network, this algorithm constructs a sparse subnetwork by sampling hidden nodes from an optimized probability distribution defined using the ridgelet transform. The quantum algorithm performs this sampling in time $O(D)$ in the data dimension $D$, whereas a naive classical implementation relies on handling exponentially many candidate nodes and hence takes $\exp[O(D)]$ time. In this work, we construct and analyze a quantum-inspired fully classical algorithm for the same sampling task. We show that our algorithm runs in time $O(\operatorname{poly}(D))$, thereby removing the exponential dependence on $D$ from the previous classical approach. Numerical simulations show that the proposed sampler achieves empirical risk comparable to exact sampling from the optimized distribution and substantially lower than sampling from the non-optimized uniform distribution, while also exhibiting exponentially improved runtime scaling compared with the conventional classical implementation. These successful dequantization results show that sparse subnetwork selection via optimized sampling can be achieved classically with polynomial data-dimension scaling on conventional computers without quantum hardware, providing an alternative to the existing quantum algorithm.

Comments
28 pages, 3 figures

Related papers

Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation

Hayata Yamasaki, Sathyawageeswar Subramanian, Satoshi Hayakawa +1 more

A significant challenge in the field of quantum machine learning (QML) is to establish applications of quantum computation to accelerate common tasks in machine learning such as those for neural networks. Ridgelet transform has been a fundamental mathematical tool in the theoretical studies of neural networks, but the practical applicability of ridgelet transform to conducting learning tasks was limited since its numerical implementation by conventional classical computation requires an exponential runtime $\exp(O(D))$ as data dimension $D$ increases. To address this problem, we develop a quantum ridgelet transform (QRT), which implements the ridgelet transform of a quantum state within a linear runtime $O(D)$ of quantum computation. As an application, we also 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 without conducting large-scale optimization of the original network. This application discovers an efficient way in this regime to demonstrate the lottery ticket hypothesis on finding such a sparse trainable neural network. These results open an avenue of QML for accelerating learning tasks with commonly used classical neural networks.

arXiv:2301.11936•Jan 27, 2023•2 citations

A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features

Natsuto Isogai, Mio Murao, Hayata Yamasaki

Quantum-inspired classical algorithms have dequantized several quantum machine learning routines by replacing quantum linear-algebra subroutines with classical counterparts. However, the sampler based on quantum singular value transformation (QSVT) for learning with optimized random features is not covered by existing dequantization frameworks, because the matrix to be inverted is not itself available through sampling access. In this work, we develop a classical algorithm to address this type of quantum-advantage candidate. Our method samples heavy indices, reduces the transformation to a small principal block, and outputs a sparse classical representation with operator-norm guarantees. Applying this method dequantizes the sampler for optimized random features, giving a classical sampler with prescribed accuracy and polynomially related runtime. These results show that the factorization underlying a quantum block encoding can itself provide sufficient classical structure even when sampling-and-query access to the composite matrix is unavailable.

quant-pharXiv:2609.10729•Sep 11, 2026•2 citations

Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions

Hayata Yamasaki, Sathyawageeswar Subramanian, Sho Sonoda +1 more

Kernel methods augmented with random features give scalable algorithms for learning from big data. But it has been computationally hard to sample random features according to a probability distribution that is optimized for the data, so as to minimize the required number of features for achieving the learning to a desired accuracy. Here, we develop a quantum algorithm for sampling from this optimized distribution over features, in runtime $O(D)$ that is linear in the dimension $D$ of the input data. Our algorithm achieves an exponential speedup in $D$ compared to any known classical algorithm for this sampling task. In contrast to existing quantum machine learning algorithms, our algorithm circumvents sparsity and low-rank assumptions and thus has wide applicability. We also show that the sampled features can be combined with regression by stochastic gradient descent to achieve the learning without canceling out our exponential speedup. Our algorithm based on sampling optimized random features leads to an accelerated framework for machine learning that takes advantage of quantum computers.

arXiv:2004.10756•Apr 22, 2020•13 citations

Strong Lottery Ticket Hypothesis for Quantum Neural Networks

Hongkyun Kwon, Hyun Kyu Lee, Joongheon Kim +1 more

Quantum Neural Networks (QNNs) possess high expressivity via rich unitary transformations, offering abundant representational capacity while maintaining a parameter-effective architecture. In classical deep learning, the high expressivity of deep neural networks (DNNs) motivates the Strong Lottery Ticket Hypothesis (SLTH), which suggests that a randomly initialized DNN contains sparse subnetworks that achieve high performance immediately or serve as a warm start. On the quantum side, a key question is: Does a strong lottery ticket exist in QNNs? Our answer is, Quantum-Strong Lottery Ticket Hypothesis (Q-SLTH), i.e., the first theoretical analysis for the existence of high-performing subnetworks in random scratch of QNNs. We validate our theory by proposing a quantum edge-popup algorithm to find strong subnetworks and empirically identifying winning tickets in randomly initialized QNNs on the MNIST and Fashion-MNIST benchmarks. For practice, Q-SLTH suggests a way to compress QNNs, allowing them to use fewer gates and thereby mitigating quantum-noise-induced degradation that is amplified across multiple layers of quantum gates.

ACM International Conference on Information and Knowledge Management (CIKM)•Nov 3, 2026•0 citations

Quantum-Inspired Optimization of Large-Scale Machine Learning Algorithms

Jincheng Zhang

Large-scale machine learning (ML) models, particularly deep neural networks, often present significant challenges for traditional optimization algorithms. These algorithms, rooted in classical mechanics, frequently encounter issues such as getting trapped in local optima, high computational cost, and difficulty in handling complex, non-convex landscapes. This paper investigates the application of quantum-inspired optimization techniques to address these challenges. We explore how concepts derived from quantum phenomena – such as quantum annealing and quantum walks – can be adapted to efficiently navigate and optimize large-scale ML models. The core idea is to leverage the probabilistic and superposition properties inherent in quantum mechanics to escape local optima and accelerate the convergence process. We present a framework for designing and implementing quantum-inspired optimization strategies, focusing on the theoretical foundations and potential benefits. The proposed approach aims to provide a novel and effective solution for optimizing complex ML models, ultimately improving model performance and reducing training time. This work contributes to the growing field of quantum machine learning and offers a promising avenue for tackling the optimization problems inherent in large-scale ML.

•Sep 7, 2026•0 citations

A quantum algorithm for training wide and deep classical neural networks

Alexander Zlokapa, Hartmut Neven, Seth Lloyd

Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to $O(1/n)$ error for a training set of size $n$ by performing sparse matrix inversion in $O(\log n)$ time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for $O(\log n)$ training of a convolutional neural network with pooling.

arXiv:2107.09200•Jul 19, 2021•23 citations
Quantum machine learning (QML) aims to accelerate machine learning tasks by exploiting quantum computation. Previous work studied a QML algorithm for selecting sparse subnetworks from large shallow neural networks. Instead of directly solving an optimization problem over a large-scale network, this algorithm constructs a sparse subnetwork by sampling hidden nodes from an optimized probability distribution defined using the ridgelet transform. The quantum algorithm performs this sampling in time O(D)O(D)O(D) in the data dimension DDD, whereas a naive classical implementation relies on handling exponentially many candidate nodes and hence takes exp⁡[O(D)]\exp[O(D)]exp[O(D)] time. In this work, we construct and analyze a quantum-inspired fully classical algorithm for the same sampling task. We show that our algorithm runs in time O(poly⁡(D))O(\operatorname{poly}(D))O(poly(D)), thereby removing the exponential dependence on DDD from the previous classical approach. Numerical simulations show that the proposed sampler achieves empirical risk comparable to exact sampling from the optimized distribution and substantially lower than sampling from the non-optimized uniform distribution, while also exhibiting exponentially improved runtime scaling compared with the conventional classical implementation. These successful dequantization results show that sparse subnetwork selection via optimized sampling can be achieved classically with polynomial data-dimension scaling on conventional computers without quantum hardware, providing an alternative to the existing quantum algorithm.
A significant challenge in the field of quantum machine learning (QML) is to establish applications of quantum computation to accelerate common tasks in machine learning such as those for neural networks. Ridgelet transform has been a fundamental mathematical tool in the theoretical studies of neural networks, but the practical applicability of ridgelet transform to conducting learning tasks was limited since its numerical implementation by conventional classical computation requires an exponential runtime exp⁡(O(D))\exp(O(D))exp(O(D)) as data dimension DDD increases. To address this problem, we develop a quantum ridgelet transform (QRT), which implements the ridgelet transform of a quantum state within a linear runtime O(D)O(D)O(D) of quantum computation. As an application, we also 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 without conducting large-scale optimization of the original network. This application discovers an efficient way in this regime to demonstrate the lottery ticket hypothesis on finding such a sparse trainable neural network. These results open an avenue of QML for accelerating learning tasks with commonly used classical neural networks.
Quantum-inspired classical algorithms have dequantized several quantum machine learning routines by replacing quantum linear-algebra subroutines with classical counterparts. However, the sampler based on quantum singular value transformation (QSVT) for learning with optimized random features is not covered by existing dequantization frameworks, because the matrix to be inverted is not itself available through sampling access. In this work, we develop a classical algorithm to address this type of quantum-advantage candidate. Our method samples heavy indices, reduces the transformation to a small principal block, and outputs a sparse classical representation with operator-norm guarantees. Applying this method dequantizes the sampler for optimized random features, giving a classical sampler with prescribed accuracy and polynomially related runtime. These results show that the factorization underlying a quantum block encoding can itself provide sufficient classical structure even when sampling-and-query access to the composite matrix is unavailable.
Kernel methods augmented with random features give scalable algorithms for learning from big data. But it has been computationally hard to sample random features according to a probability distribution that is optimized for the data, so as to minimize the required number of features for achieving the learning to a desired accuracy. Here, we develop a quantum algorithm for sampling from this optimized distribution over features, in runtime O(D)O(D)O(D) that is linear in the dimension DDD of the input data. Our algorithm achieves an exponential speedup in DDD compared to any known classical algorithm for this sampling task. In contrast to existing quantum machine learning algorithms, our algorithm circumvents sparsity and low-rank assumptions and thus has wide applicability. We also show that the sampled features can be combined with regression by stochastic gradient descent to achieve the learning without canceling out our exponential speedup. Our algorithm based on sampling optimized random features leads to an accelerated framework for machine learning that takes advantage of quantum computers.
Quantum Neural Networks (QNNs) possess high expressivity via rich unitary transformations, offering abundant representational capacity while maintaining a parameter-effective architecture. In classical deep learning, the high expressivity of deep neural networks (DNNs) motivates the Strong Lottery Ticket Hypothesis (SLTH), which suggests that a randomly initialized DNN contains sparse subnetworks that achieve high performance immediately or serve as a warm start. On the quantum side, a key question is: Does a strong lottery ticket exist in QNNs? Our answer is, Quantum-Strong Lottery Ticket Hypothesis (Q-SLTH), i.e., the first theoretical analysis for the existence of high-performing subnetworks in random scratch of QNNs. We validate our theory by proposing a quantum edge-popup algorithm to find strong subnetworks and empirically identifying winning tickets in randomly initialized QNNs on the MNIST and Fashion-MNIST benchmarks. For practice, Q-SLTH suggests a way to compress QNNs, allowing them to use fewer gates and thereby mitigating quantum-noise-induced degradation that is amplified across multiple layers of quantum gates.
Large-scale machine learning (ML) models, particularly deep neural networks, often present significant challenges for traditional optimization algorithms. These algorithms, rooted in classical mechanics, frequently encounter issues such as getting trapped in local optima, high computational cost, and difficulty in handling complex, non-convex landscapes. This paper investigates the application of quantum-inspired optimization techniques to address these challenges. We explore how concepts derived from quantum phenomena – such as quantum annealing and quantum walks – can be adapted to efficiently navigate and optimize large-scale ML models. The core idea is to leverage the probabilistic and superposition properties inherent in quantum mechanics to escape local optima and accelerate the convergence process. We present a framework for designing and implementing quantum-inspired optimization strategies, focusing on the theoretical foundations and potential benefits. The proposed approach aims to provide a novel and effective solution for optimizing complex ML models, ultimately improving model performance and reducing training time. This work contributes to the growing field of quantum machine learning and offers a promising avenue for tackling the optimization problems inherent in large-scale ML.
Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to O(1/n)O(1/n)O(1/n) error for a training set of size nnn by performing sparse matrix inversion in O(log⁡n)O(\log n)O(logn) time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for O(log⁡n)O(\log n)O(logn) training of a convolutional neural network with pooling.