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:1710.07063

Quantum-classical truncated Newton method for high-dimensional energy landscapes

Leonard Wossnig, Sebastian Tschiatschek, Stefan Zohren

Published Oct 19, 2017• 2 citations
arXivHTMLPDF

Abstract

We develop a quantum-classical hybrid algorithm for function optimization that is particularly useful in the training of neural networks since it makes use of particular aspects of high-dimensional energy landscapes. Due to a recent formulation of semi-supervised learning as an optimization problem, the algorithm can further be used to find the optimal model parameters for deep generative models. In particular, we present a truncated saddle-free Newton's method based on recent insight from optimization, analysis of deep neural networks and random matrix theory. By combining these with the specific quantum subroutines we are able to exhaust quantum computing in order to arrive at a new quantum-classical hybrid algorithm design. Our algorithm is expected to perform at least as well as existing classical algorithms while achieving a polynomial speedup. The speedup is limited by the required classical read-out. Omitting this requirement can in theory lead to an exponential speedup.

DOI
10.48550/arxiv.1710.07063

Related papers

Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent

Pingzhi Li, Junyu Liu, Hanrui Wang +1 more

Optimization techniques in deep learning are predominantly led by first-order gradient methodologies, such as SGD. However, neural network training can greatly benefit from the rapid convergence characteristics of second-order optimization. Newton's GD stands out in this category, by rescaling the gradient using the inverse Hessian. Nevertheless, one of its major bottlenecks is matrix inversion, which is notably time-consuming in $O(N^3)$ time with weak scalability. Matrix inversion can be translated into solving a series of linear equations. Given that quantum linear solver algorithms (QLSAs), leveraging the principles of quantum superposition and entanglement, can operate within a $\text{polylog}(N)$ time frame, they present a promising approach with exponential acceleration. Specifically, one of the most recent QLSAs demonstrates a complexity scaling of $O(d\cdotκ\log(N\cdotκ/ε))$, depending on: {size~$N$, condition number~$κ$, error tolerance~$ε$, quantum oracle sparsity~$d$} of the matrix. However, this also implies that their potential exponential advantage may be hindered by certain properties (i.e. $κ$ and $d$). We propose Q-Newton, a hybrid quantum-classical scheduler for accelerating neural network training with Newton's GD. Q-Newton utilizes a streamlined scheduling module that coordinates between quantum and classical linear solvers, by estimating & reducing $κ$ and constructing $d$ for the quantum solver. Our evaluation showcases the potential for Q-Newton to significantly reduce the total training time compared to commonly used optimizers like SGD. We hypothesize a future scenario where the gate time of quantum machines is reduced, possibly realized by attoseconds physics. Our evaluation establishes an ambitious and promising target for the evolution of quantum computing.

arXiv:2405.00252•Apr 30, 2024•2 citations

Fast variational quantum algorithms for training neural networks and solving convex optimizations

Changpeng Shao

Variational hybrid quantum classical algorithms to optimizations are important applications for near-term quantum computing. This paper proposes two quantum algorithms (the second one is variational) for training neural networks. Both of them obtain exponential speedup at the number of samples and polynomial speedup at the dimension of the samples over classical training algorithms. Moreover, the proposed quantum algorithms return the classical information of the training weight so that the outputs can be used directly to solve other problems. For practicality, we draw the quantum circuits to implement the two algorithms. Finally, as an inspiration, we show how to apply the variational algorithm to achieve speedup at the number of constraints in solving convex optimization problems.

Physical Review A•Apr 17, 2019•13 citations

Hybrid Quantum Classical Deep Learning Models for Real-Time Intelligent Systems

Tareq Ahmed, Samer Abrar, Tarbiat Modares

Artificial intelligence (AI) and Quantum Computing are two rapidly advancing technological areas, which can present new opportunities for designing intelligent systems with the ability to perform adaptive learning, especially when considering real-time applications that require significant computational capacity. With the advent of hybrid quantum–classical deep learning models: a completely new paradigm that combines well performing classical neural networks with computational advantages given by quantum mechanics phenomena such as superposition, entanglement and parallelism into one model type—models strong on both supervised a unsupervised tasks. Abstract here, we address architectural design, optimization methods and real-time implementation of hybrid quantum– classical systems. Quantum circuits learn all the feature representations and speed up calculations which, in real-time under classical computation will become frustratingly intensive, however, deep learning frameworks scale up using computing resources running independently of quantum processes. It investigates novel hybrid architectures including, e.g., Variational quantum circuits and deep neural networks hybrids and evaluates implemented applications of the new ones for intelligent real-time systems as e.g. autonomous vehicles or smart healthcare monitors as well industrial automations from now until at least October 2023. Novel approaches like quantum-informed training techniques and hybrid optimizers are effectively solving major problems in the industry including noise due to quantum hardware, data encoding constraints, and scalability limitations. Moreover, it designs a novel latency-aware hybrid learning framework to ensure effective decision-making within time-sensitive situations. It has been shown by both experimental evidence and theoretical analysis that purely classical approaches can be outperformed in hybrid models, particularly for high-dimensional data problems that require complex optimization. Lastly, integrated with quantum fault-tolerant computing and adaptive hybrid learning ecosystems, some future directions are laid as conclusions in the end of research.

International Journal of Quantum Computing and Artificial Intelligence (IJQCAI)•Jan 1, 2026•0 citations

Quantum-enhanced training of large language models: a hybrid approach

Nan Wu, Fangmin Song, Xiangdong Li

Significant computational challenges exist in the training of large language models (LLMs), specifically for the efficient convergence. This paper discusses a hybrid quantum-classical framework designed to address these challenges. With the integration of quantum computing principles, like the superposition, entanglement, and tunneling, into the classical deep learning methods, an approach is studied to accelerate convergence, enhance optimization efficiency, and improve model generalization. A quantum feature mapping is used to project classical data into high-dimensional Hilbert spaces, enhancing data representation and revealing more complex feature patterns in the data. The quantum-assisted optimization algorithms, like Quantum Approximate Optimization Algorithm (QAOA) and Variational Quantum Eigensolver (VQE), can efficiently find optimal solutions within complex, non-convex loss landscapes and mitigate the issues of local minima encountered by classical methods. Furthermore, the quantum-accelerated matrix operations, with the use of Harrow-Hassidim-Lloyd (HHL) algorithm or Quantum Fourier Transform (QFT) etc., can provide computational speed-ups for the LLM training. Quantum measurement introduces inherent randomness, similar to the dropout in deep neural networks, where certain neurons are randomly deactivated during training. In the noisy intermediate-scale quantum (NISQ) era, our quantum-classical framework and conceptual analyses demonstrate the feasibility and potential advantages. This work lays the foundation for future research in this area.

SPIE Quantum Information Science, Sensing, and Computation•Apr 11, 2025•0 citations

Quantum-Inspired Optimization of Neural Network Training Dynamics

Jincheng Zhang

Training deep neural networks remains a computationally intensive and often challenging process. Traditional optimization methods, such as stochastic gradient descent (SGD) and its variants, frequently struggle to escape local minima and converge to optimal solutions, leading to suboptimal network performance. This paper proposes a novel approach to neural network training that leverages principles inspired by quantum mechanics. Specifically, we investigate the application of quantum-inspired optimization techniques, including simulated annealing and quantum walks, to dynamically adjust the training process. The core idea is to mimic the probabilistic exploration inherent in quantum systems to effectively navigate the complex loss landscape of neural networks. We formulate the training process as a quantum-inspired optimization problem, where the network's weights are treated as quantum bits (Qubits) and the optimization algorithm seeks to find the lowest energy state, analogous to finding the minimum loss. The proposed method demonstrates the potential for accelerating convergence and improving the overall accuracy of neural networks compared to conventional optimization strategies. Our analysis focuses on the key aspects of the approach, including the mathematical formulation of the quantum-inspired optimization problem and the selection of appropriate parameters to govern the exploration and exploitation phases. We present a theoretical framework for understanding the dynamics of this approach and discuss potential avenues for further research, including hybrid quantum-classical algorithms and the integration of quantum computing hardware.

•Sep 5, 2026•0 citations

Title: Quantum-Classical Hybrid Constraint Optimization for Complex Neural Networks

Jincheng Zhang

Quantum-Classical Hybrid Constraint Optimization (QCHCO) represents a novel approach to training complex neural networks by dynamically integrating quantum-enhanced exploration with classical optimization. This research investigates the potential of a hybrid algorithm that leverages quantum tunneling to navigate high-dimensional, non-convex optimization landscapes, offering a pathway to overcome current limitations in neural network design. This paper outlines the core mechanism, discusses the rationale behind its design, and presents preliminary results demonstrating the effectiveness of this hybrid optimization strategy in a specific neural network training scenario. The core claim centers on the ability to effectively explore and optimize neural network architectures with unprecedented complexity and robustness.

•Aug 31, 2026•0 citations
We develop a quantum-classical hybrid algorithm for function optimization that is particularly useful in the training of neural networks since it makes use of particular aspects of high-dimensional energy landscapes. Due to a recent formulation of semi-supervised learning as an optimization problem, the algorithm can further be used to find the optimal model parameters for deep generative models. In particular, we present a truncated saddle-free Newton's method based on recent insight from optimization, analysis of deep neural networks and random matrix theory. By combining these with the specific quantum subroutines we are able to exhaust quantum computing in order to arrive at a new quantum-classical hybrid algorithm design. Our algorithm is expected to perform at least as well as existing classical algorithms while achieving a polynomial speedup. The speedup is limited by the required classical read-out. Omitting this requirement can in theory lead to an exponential speedup.
Optimization techniques in deep learning are predominantly led by first-order gradient methodologies, such as SGD. However, neural network training can greatly benefit from the rapid convergence characteristics of second-order optimization. Newton's GD stands out in this category, by rescaling the gradient using the inverse Hessian. Nevertheless, one of its major bottlenecks is matrix inversion, which is notably time-consuming in O(N3)O(N^3)O(N3) time with weak scalability. Matrix inversion can be translated into solving a series of linear equations. Given that quantum linear solver algorithms (QLSAs), leveraging the principles of quantum superposition and entanglement, can operate within a polylog(N)\text{polylog}(N)polylog(N) time frame, they present a promising approach with exponential acceleration. Specifically, one of the most recent QLSAs demonstrates a complexity scaling of O(d⋅κlog⁡(N⋅κ/ε))O(d\cdotκ\log(N\cdotκ/ε))O(d⋅κlog(N⋅κ/ε)), depending on: {size~NNN, condition number~κκκ, error tolerance~εεε, quantum oracle sparsity~ddd} of the matrix. However, this also implies that their potential exponential advantage may be hindered by certain properties (i.e. κκκ and ddd). We propose Q-Newton, a hybrid quantum-classical scheduler for accelerating neural network training with Newton's GD. Q-Newton utilizes a streamlined scheduling module that coordinates between quantum and classical linear solvers, by estimating & reducing κκκ and constructing ddd for the quantum solver. Our evaluation showcases the potential for Q-Newton to significantly reduce the total training time compared to commonly used optimizers like SGD. We hypothesize a future scenario where the gate time of quantum machines is reduced, possibly realized by attoseconds physics. Our evaluation establishes an ambitious and promising target for the evolution of quantum computing.
Variational hybrid quantum classical algorithms to optimizations are important applications for near-term quantum computing. This paper proposes two quantum algorithms (the second one is variational) for training neural networks. Both of them obtain exponential speedup at the number of samples and polynomial speedup at the dimension of the samples over classical training algorithms. Moreover, the proposed quantum algorithms return the classical information of the training weight so that the outputs can be used directly to solve other problems. For practicality, we draw the quantum circuits to implement the two algorithms. Finally, as an inspiration, we show how to apply the variational algorithm to achieve speedup at the number of constraints in solving convex optimization problems.
Artificial intelligence (AI) and Quantum Computing are two rapidly advancing technological areas, which can present new opportunities for designing intelligent systems with the ability to perform adaptive learning, especially when considering real-time applications that require significant computational capacity. With the advent of hybrid quantum–classical deep learning models: a completely new paradigm that combines well performing classical neural networks with computational advantages given by quantum mechanics phenomena such as superposition, entanglement and parallelism into one model type—models strong on both supervised a unsupervised tasks. Abstract here, we address architectural design, optimization methods and real-time implementation of hybrid quantum– classical systems. Quantum circuits learn all the feature representations and speed up calculations which, in real-time under classical computation will become frustratingly intensive, however, deep learning frameworks scale up using computing resources running independently of quantum processes. It investigates novel hybrid architectures including, e.g., Variational quantum circuits and deep neural networks hybrids and evaluates implemented applications of the new ones for intelligent real-time systems as e.g. autonomous vehicles or smart healthcare monitors as well industrial automations from now until at least October 2023. Novel approaches like quantum-informed training techniques and hybrid optimizers are effectively solving major problems in the industry including noise due to quantum hardware, data encoding constraints, and scalability limitations. Moreover, it designs a novel latency-aware hybrid learning framework to ensure effective decision-making within time-sensitive situations. It has been shown by both experimental evidence and theoretical analysis that purely classical approaches can be outperformed in hybrid models, particularly for high-dimensional data problems that require complex optimization. Lastly, integrated with quantum fault-tolerant computing and adaptive hybrid learning ecosystems, some future directions are laid as conclusions in the end of research.
Significant computational challenges exist in the training of large language models (LLMs), specifically for the efficient convergence. This paper discusses a hybrid quantum-classical framework designed to address these challenges. With the integration of quantum computing principles, like the superposition, entanglement, and tunneling, into the classical deep learning methods, an approach is studied to accelerate convergence, enhance optimization efficiency, and improve model generalization. A quantum feature mapping is used to project classical data into high-dimensional Hilbert spaces, enhancing data representation and revealing more complex feature patterns in the data. The quantum-assisted optimization algorithms, like Quantum Approximate Optimization Algorithm (QAOA) and Variational Quantum Eigensolver (VQE), can efficiently find optimal solutions within complex, non-convex loss landscapes and mitigate the issues of local minima encountered by classical methods. Furthermore, the quantum-accelerated matrix operations, with the use of Harrow-Hassidim-Lloyd (HHL) algorithm or Quantum Fourier Transform (QFT) etc., can provide computational speed-ups for the LLM training. Quantum measurement introduces inherent randomness, similar to the dropout in deep neural networks, where certain neurons are randomly deactivated during training. In the noisy intermediate-scale quantum (NISQ) era, our quantum-classical framework and conceptual analyses demonstrate the feasibility and potential advantages. This work lays the foundation for future research in this area.
Training deep neural networks remains a computationally intensive and often challenging process. Traditional optimization methods, such as stochastic gradient descent (SGD) and its variants, frequently struggle to escape local minima and converge to optimal solutions, leading to suboptimal network performance. This paper proposes a novel approach to neural network training that leverages principles inspired by quantum mechanics. Specifically, we investigate the application of quantum-inspired optimization techniques, including simulated annealing and quantum walks, to dynamically adjust the training process. The core idea is to mimic the probabilistic exploration inherent in quantum systems to effectively navigate the complex loss landscape of neural networks. We formulate the training process as a quantum-inspired optimization problem, where the network's weights are treated as quantum bits (Qubits) and the optimization algorithm seeks to find the lowest energy state, analogous to finding the minimum loss. The proposed method demonstrates the potential for accelerating convergence and improving the overall accuracy of neural networks compared to conventional optimization strategies. Our analysis focuses on the key aspects of the approach, including the mathematical formulation of the quantum-inspired optimization problem and the selection of appropriate parameters to govern the exploration and exploitation phases. We present a theoretical framework for understanding the dynamics of this approach and discuss potential avenues for further research, including hybrid quantum-classical algorithms and the integration of quantum computing hardware.
Quantum-Classical Hybrid Constraint Optimization (QCHCO) represents a novel approach to training complex neural networks by dynamically integrating quantum-enhanced exploration with classical optimization. This research investigates the potential of a hybrid algorithm that leverages quantum tunneling to navigate high-dimensional, non-convex optimization landscapes, offering a pathway to overcome current limitations in neural network design. This paper outlines the core mechanism, discusses the rationale behind its design, and presents preliminary results demonstrating the effectiveness of this hybrid optimization strategy in a specific neural network training scenario. The core claim centers on the ability to effectively explore and optimize neural network architectures with unprecedented complexity and robustness.