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

New Journal of Physics

Quantum speed-up in global optimization of binary neural nets

Yidong Liao, Daniel Ebler, Feiyang Liu, Oscar Dahlsten

Published Nov 12, 2020• 4 citations
Publisher

Abstract

Abstract The performance of a neural network (NN) for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This includes networks with binary weights, an important class of networks due to their practical hardware implementations. We therefore suggest an alternative approach to training binary NNs. It utilizes a quantum superposition of weight configurations. We show that the quantum training guarantees with high probability convergence towards the globally optimal set of network parameters. This resolves two prominent issues of classical training: (1) the vanishing gradient problem and (2) common convergence to sub-optimal network parameters. We prove that a solution is found after approximately 4 n 2 log n δ N ˜ calls to a comparing oracle, where δ represents a precision, n is the number of training inputs and N ˜ is the number of weight configurations. We give the explicit algorithm and implement it in numerical simulations.

DOI
10.1088/1367-2630/abc9ef

Related papers

Quantum advantage in training binary neural networks

Yidong Liao, Daniel Ebler, Feiyang Liu +1 more

The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This includes networks with binary weights, an important class of networks due to their practical hardware implementations. We therefore suggest an alternative approach to training binary neural networks. It utilizes a quantum superposition of weight configurations. We show that the quantum training guarantees with high probability convergence towards the globally optimal set of network parameters. This resolves two prominent issues of classical training: (1) the vanishing gradient problem and (2) common convergence to suboptimal network parameters. Moreover we achieve a provable polynomial---sometimes exponential---speedup over classical training for certain classes of tasks. We design an explicit training algorithm and implement it in numerical simulations.

arXiv:1810.12948•Oct 30, 2018•3 citations

Toward Trainability of Quantum Neural Networks

Kaining Zhang, Min-Hsiu Hsieh, Liu Liu +1 more

Quantum Neural Networks (QNNs) have been recently proposed as generalizations of classical neural networks to achieve the quantum speed-up. Despite the potential to outperform classical models, serious bottlenecks exist for training QNNs; namely, QNNs with random structures have poor trainability due to the vanishing gradient with rate exponential to the input qubit number. The vanishing gradient could seriously influence the applications of large-size QNNs. In this work, we provide a viable solution with theoretical guarantees. Specifically, we prove that QNNs with tree tensor and step controlled architectures have gradients that vanish at most polynomially with the qubit number. We numerically demonstrate QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.

arXiv:2011.06258•Nov 12, 2020•35 citations

Training Ensembles of Quantum Binary Neural Networks

Daivid V. Leal, Tiago De Lima, Adenilton José da Silva

Artificial Neural Networks (NNs) are applied to solve problems in several fields such as translation, image processing, and diagnosis of diseases. Training NNs and searching weights parameters for them is a costly task that depends on weights initialization. This problem cost increases when it is necessary to train an Ensemble of Neural Networks (ENNs). Some works explore ways to train Binary Neural Networks (BNNs) using quantum techniques with success. This paper shows a hybrid approach to train an Ensemble of Binary Neural Networks with the same computational cost to train one variational quantum circuit.

International Joint Conference on Neural Networks (IJCNN)•Jul 18, 2021•3 citations

Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition

Juan Carrasquilla, Mohamed Hibat-Allah, Estelle M. Inack +4 more

Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in a single optimization loop. Through classical simulations, we demonstrate that our approach effectively finds optimal parameters, hyperparameters and architectural choices with high probability on classification problems including a two-dimensional Gaussian dataset and a scaled-down version of the MNIST handwritten digits. We represent our quantum hypernetworks as variational quantum circuits, and find that an optimal circuit depth maximizes the probability of finding performant binary neural networks. Our unified approach provides an immense scope for other applications in the field of machine learning.

arXiv:2301.08292•Jan 19, 2023•1 citation

Training neural networks with universal adiabatic quantum computing

Steven Adam Abel, Juan Carlos Criado, Michael Spannowsky

The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This article presents a novel approach to NN training using adiabatic quantum computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimization problems. We propose a universal AQC method that can be implemented on gate quantum computers, allowing for a broad range of Hamiltonians and thus enabling the training of expressive neural networks. We apply this approach to various neural networks with continuous, discrete, and binary weights. The study results indicate that AQC can very efficiently evaluate the global minimum of the loss function, offering a promising alternative to classical training methods.

arXiv:2308.13028•Frontiers in Artificial Intelligence•Jun 21, 2024•3 citations

Grover's Implementation of Quantum Binary Neural Networks

Brody Wrighter, Sonia López Alarcón

Binary Neural Networks (BNNs) are the result of a simplification of network parameters in Artificial Neural Networks (ANNs). The computational complexity of training ANNs increases significantly as the size of the network increases. This complexity can be greatly reduced if the parameters of the network are binarized. Binarization, which is a one bit quantization, can also come with complications including error and information loss. The implementation of BNNs on quantum hardware could potentially provide a computational advantage over its classical counterpart. This is due to the fact that binarized parameters fit nicely to the nature of quantum hardware. Quantum superposition allows the network to be trained more efficiently, without using back propagation techniques, with the application of Grover's Algorithm for the training process. This paper looks into two BNN designs that utilize only quantum hardware, as opposed to hybrid quantum-classical implementations. It also provides practical implementations for both of them. Looking into their scalability, improvements on the design are proposed to reduce complexity even further.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•2 citations
Abstract The performance of a neural network (NN) for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This includes networks with binary weights, an important class of networks due to their practical hardware implementations. We therefore suggest an alternative approach to training binary NNs. It utilizes a quantum superposition of weight configurations. We show that the quantum training guarantees with high probability convergence towards the globally optimal set of network parameters. This resolves two prominent issues of classical training: (1) the vanishing gradient problem and (2) common convergence to sub-optimal network parameters. We prove that a solution is found after approximately 4 n 2 log n δ N ˜ calls to a comparing oracle, where δ represents a precision, n is the number of training inputs and N ˜ is the number of weight configurations. We give the explicit algorithm and implement it in numerical simulations.
The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This includes networks with binary weights, an important class of networks due to their practical hardware implementations. We therefore suggest an alternative approach to training binary neural networks. It utilizes a quantum superposition of weight configurations. We show that the quantum training guarantees with high probability convergence towards the globally optimal set of network parameters. This resolves two prominent issues of classical training: (1) the vanishing gradient problem and (2) common convergence to suboptimal network parameters. Moreover we achieve a provable polynomial---sometimes exponential---speedup over classical training for certain classes of tasks. We design an explicit training algorithm and implement it in numerical simulations.
Quantum Neural Networks (QNNs) have been recently proposed as generalizations of classical neural networks to achieve the quantum speed-up. Despite the potential to outperform classical models, serious bottlenecks exist for training QNNs; namely, QNNs with random structures have poor trainability due to the vanishing gradient with rate exponential to the input qubit number. The vanishing gradient could seriously influence the applications of large-size QNNs. In this work, we provide a viable solution with theoretical guarantees. Specifically, we prove that QNNs with tree tensor and step controlled architectures have gradients that vanish at most polynomially with the qubit number. We numerically demonstrate QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.
Artificial Neural Networks (NNs) are applied to solve problems in several fields such as translation, image processing, and diagnosis of diseases. Training NNs and searching weights parameters for them is a costly task that depends on weights initialization. This problem cost increases when it is necessary to train an Ensemble of Neural Networks (ENNs). Some works explore ways to train Binary Neural Networks (BNNs) using quantum techniques with success. This paper shows a hybrid approach to train an Ensemble of Binary Neural Networks with the same computational cost to train one variational quantum circuit.
Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in a single optimization loop. Through classical simulations, we demonstrate that our approach effectively finds optimal parameters, hyperparameters and architectural choices with high probability on classification problems including a two-dimensional Gaussian dataset and a scaled-down version of the MNIST handwritten digits. We represent our quantum hypernetworks as variational quantum circuits, and find that an optimal circuit depth maximizes the probability of finding performant binary neural networks. Our unified approach provides an immense scope for other applications in the field of machine learning.
The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This article presents a novel approach to NN training using adiabatic quantum computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimization problems. We propose a universal AQC method that can be implemented on gate quantum computers, allowing for a broad range of Hamiltonians and thus enabling the training of expressive neural networks. We apply this approach to various neural networks with continuous, discrete, and binary weights. The study results indicate that AQC can very efficiently evaluate the global minimum of the loss function, offering a promising alternative to classical training methods.
Binary Neural Networks (BNNs) are the result of a simplification of network parameters in Artificial Neural Networks (ANNs). The computational complexity of training ANNs increases significantly as the size of the network increases. This complexity can be greatly reduced if the parameters of the network are binarized. Binarization, which is a one bit quantization, can also come with complications including error and information loss. The implementation of BNNs on quantum hardware could potentially provide a computational advantage over its classical counterpart. This is due to the fact that binarized parameters fit nicely to the nature of quantum hardware. Quantum superposition allows the network to be trained more efficiently, without using back propagation techniques, with the application of Grover's Algorithm for the training process. This paper looks into two BNN designs that utilize only quantum hardware, as opposed to hybrid quantum-classical implementations. It also provides practical implementations for both of them. Looking into their scalability, improvements on the design are proposed to reduce complexity even further.