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

Knowledge-Based Systems

A Noisy Optimization mechanism for variational quantum classifiers

Rodica Ioana Lung, Florin Sebastian Duma

Published Mar 7, 2026• 0 citations
Publisher

Abstract

• existence of barren plateaux is one of the challenges in the practical use of variational quantum classifiers; • a noise-based mechanism that shifts training data during optimization, helping escape barren plateaux, is proposed; • the approach is tested with a variational quantum classifier modeling BET index changes using other indices from Europe and the United States; • simulations use the Pennylane framework. The barren plateaux phenomenon has been identified as a significant challenge for variational quantum algorithms, particularly for classification tasks. In this article, we propose a novel approach to mitigating this problem for variational quantum classifiers during the optimization phase. The noisy optimization mechanism shifts the training data by adding a small amount of uniform noise, thereby inducing changes in the parameters being searched. The effectiveness of the method is evaluated using real financial data, modeling the evolution of the BET index in relation to well-known indices from neighboring Central and Eastern European countries, as well as from Western Europe and the United States. The results demonstrate that this approach significantly improves upon the corresponding baseline quantum classifier and provides results comparable to those of established classical methods.

DOI
10.1016/j.knosys.2026.115659

Related papers

A Comparison of Evolutionary Algorithms for Training Variational Quantum Classifiers

Giovanni Acampora, Angela Chiatto, Autilia Vitiello

Quantum machine learning is a research area that explores the interplay of ideas from quantum computing and machine learning to speed up the time it takes to train or evaluate a machine learning model. Variational quantum classifiers are among the most widely used quantum models for supervised machine learning and base their operation on learning free parameters through conventional optimization algorithms. In spite of their potential benefits, there is a design issue making quantum variational classifiers not fully operative: the existence of exponentially vanishing gradients, known as “barren plateau landscapes”. A barren plateau is a trainability problem that occurs in optimization algorithms for quantum machine learning when the problem-solving space turns flat as the algorithm is run. In that situation, the algorithm cannot find the downward slope in what appears to be a featureless landscape and there's no clear path to the optimum of the cost function. In this challenging scenario, evolutionary optimization techniques can be a viable choice in solving the problem because of their gradient independence. This paper introduces a comparative study involving different evolutionary algorithms to assess their suitability in acting as optimizer for a specific quantum machine learning method, known as variational quantum classifier.

IEEE Congress on Evolutionary Computation (CEC)•Jul 1, 2023•8 citations

Automatic Optimization of Variational Quantum Algorithm-Based Classifiers

Ruihong Jia, Guang Yang, Min Nie +2 more

With the advent of the era of big data, how to efficiently process data has become an urgent problem. Although classical machine learning algorithms are very mature in processing data, they require a large amount of data to complete the training process. Quantum machine learning uses the superposition, entanglement, parallelism and other characteristics of quantum computing to improve the performance of classical machine learning algorithms. At the same time, circuit optimization of the quantum classifier can reduce the computational complexity. This paper proposes an automatic optimization model of the classifier based on the variational quantum algorithm, which reduces the complexity of the parameter update process through the deep optimization of the core circuit. This model greatly speeds up the training process and has lower complexity than other quantum classifiers. In addition, a unique regularization method is used to avoid overfitting. The simulation results show that the classification of some typical data sets can achieve better classification results, and the training parameters and training speed are significantly better than other quantum classifiers. Finally, the robustness of the classifier is further verified in the presence of noise.

•Sep 23, 2022•2 citations

Mitigating barren plateaus with transfer-learning-inspired parameter initializations

Huanyu Liu, Tai-Ping Sun, Yu-Chun Wu +2 more

Abstract Variational quantum algorithms (VQAs) are widely applied in the noisy intermediate-scale quantum era and are expected to demonstrate quantum advantage. However, training VQAs faces difficulties, one of which is the so-called barren plateaus (BPs) phenomenon, where gradients of cost functions vanish exponentially with the number of qubits. In this paper, inspired by transfer learning, where knowledge of pre-solved tasks could be further used in a different but related work with training efficiency improved, we report a parameter initialization method to mitigate BP. In the method, a small-sized task is solved with a VQA. Then the ansatz and its optimum parameters are transferred to tasks with larger sizes. Numerical simulations show that this method could mitigate BP and improve training efficiency. A brief discussion on how this method can work well is also provided. This work provides a reference for mitigating BP, and therefore, VQAs could be applied to more practical problems.

arXiv:2112.10952•New Journal of Physics•Jan 1, 2023•50 citations

Escaping Barren Plateaus in Variational Quantum Algorithms Using Negative Learning Rate in Quantum Internet of Things

Ratun Rahman, Dinh C. Nguyen

Variational Quantum Algorithms (VQAs) are becoming the primary computational primitive for next-generation quantum computers, particularly those embedded as resource-constrained accelerators in the emerging Quantum Internet of Things (QIoT). However, under such device-constrained execution conditions, the scalability of learning is severely limited by barren plateaus, where gradients collapse to zero and training stalls. This poses a practical challenge to delivering VQA-enabled intelligence on QIoT endpoints, which often have few qubits, constrained shot budgets, and strict latency requirements. In this paper, we present a novel approach for escaping barren plateaus by including negative learning rates into the optimization process in QIoT devices. Our method introduces controlled instability into model training by switching between positive and negative learning phases, allowing recovery of significant gradients and exploring flatter areas in the loss landscape. We theoretically evaluate the effect of negative learning on gradient variance and propose conditions under which it helps escape from barren zones. The experimental findings on typical VQA benchmarks show consistent improvements in both convergence and simulation results over traditional optimizers. By escaping barren plateaus, our approach leads to a novel pathway for robust optimization in quantum-classical hybrid models.

quant-pharXiv:2511.22861•IEEE Internet of Things Journal•Dec 1, 2025•1 citation

An Evolutionary Strategy – Inspired Approach to Barren Plateaux Mitigation Using Local Cost Functions

Rodica Ioana Lung, Tudor Dan Mihoc

Variational quantum algorithms face optimization difficulties due to barren plateaux, particularly as system size increases. In this work, we propose an evolutionary strategy–inspired approach that adaptively selects qubits for local cost evaluation and applies small perturbations to the selected parameters to optimize the local cost function. Numerical results on the identity gate learning problem indicate that adaptive qubit prioritization can reduce optimization stagnation and improve convergence behavior compared to standard global and local cost strategies. These findings suggest that evolutionary-guided control mechanisms may complement existing local-cost-based optimization methods in variational quantum algorithms.

IEEE Congress on Evolutionary Computation (CEC)•Jun 1, 2026•0 citations

Quantum variational algorithms are swamped with traps

Eric R. Anschuetz, Bobak T. Kiani

One of the most important properties of classical neural networks is how surprisingly trainable they are, though their training algorithms typically rely on optimizing complicated, nonconvex loss functions. Previous results have shown that unlike the case in classical neural networks, variational quantum models are often not trainable. The most studied phenomenon is the onset of barren plateaus in the training landscape of these quantum models, typically when the models are very deep. This focus on barren plateaus has made the phenomenon almost synonymous with the trainability of quantum models. Here, we show that barren plateaus are only a part of the story. We prove that a wide class of variational quantum models-which are shallow, and exhibit no barren plateaus-have only a superpolynomially small fraction of local minima within any constant energy from the global minimum, rendering these models untrainable if no good initial guess of the optimal parameters is known. We also study the trainability of variational quantum algorithms from a statistical query framework, and show that noisy optimization of a wide variety of quantum models is impossible with a sub-exponential number of queries. Finally, we numerically confirm our results on a variety of problem instances. Though we exclude a wide variety of quantum algorithms here, we give reason for optimism for certain classes of variational algorithms and discuss potential ways forward in showing the practical utility of such algorithms.

arXiv:2205.05786•Nature Communications•Dec 15, 2022•307 citations
• existence of barren plateaux is one of the challenges in the practical use of variational quantum classifiers; • a noise-based mechanism that shifts training data during optimization, helping escape barren plateaux, is proposed; • the approach is tested with a variational quantum classifier modeling BET index changes using other indices from Europe and the United States; • simulations use the Pennylane framework. The barren plateaux phenomenon has been identified as a significant challenge for variational quantum algorithms, particularly for classification tasks. In this article, we propose a novel approach to mitigating this problem for variational quantum classifiers during the optimization phase. The noisy optimization mechanism shifts the training data by adding a small amount of uniform noise, thereby inducing changes in the parameters being searched. The effectiveness of the method is evaluated using real financial data, modeling the evolution of the BET index in relation to well-known indices from neighboring Central and Eastern European countries, as well as from Western Europe and the United States. The results demonstrate that this approach significantly improves upon the corresponding baseline quantum classifier and provides results comparable to those of established classical methods.
Quantum machine learning is a research area that explores the interplay of ideas from quantum computing and machine learning to speed up the time it takes to train or evaluate a machine learning model. Variational quantum classifiers are among the most widely used quantum models for supervised machine learning and base their operation on learning free parameters through conventional optimization algorithms. In spite of their potential benefits, there is a design issue making quantum variational classifiers not fully operative: the existence of exponentially vanishing gradients, known as “barren plateau landscapes”. A barren plateau is a trainability problem that occurs in optimization algorithms for quantum machine learning when the problem-solving space turns flat as the algorithm is run. In that situation, the algorithm cannot find the downward slope in what appears to be a featureless landscape and there's no clear path to the optimum of the cost function. In this challenging scenario, evolutionary optimization techniques can be a viable choice in solving the problem because of their gradient independence. This paper introduces a comparative study involving different evolutionary algorithms to assess their suitability in acting as optimizer for a specific quantum machine learning method, known as variational quantum classifier.
With the advent of the era of big data, how to efficiently process data has become an urgent problem. Although classical machine learning algorithms are very mature in processing data, they require a large amount of data to complete the training process. Quantum machine learning uses the superposition, entanglement, parallelism and other characteristics of quantum computing to improve the performance of classical machine learning algorithms. At the same time, circuit optimization of the quantum classifier can reduce the computational complexity. This paper proposes an automatic optimization model of the classifier based on the variational quantum algorithm, which reduces the complexity of the parameter update process through the deep optimization of the core circuit. This model greatly speeds up the training process and has lower complexity than other quantum classifiers. In addition, a unique regularization method is used to avoid overfitting. The simulation results show that the classification of some typical data sets can achieve better classification results, and the training parameters and training speed are significantly better than other quantum classifiers. Finally, the robustness of the classifier is further verified in the presence of noise.
Abstract Variational quantum algorithms (VQAs) are widely applied in the noisy intermediate-scale quantum era and are expected to demonstrate quantum advantage. However, training VQAs faces difficulties, one of which is the so-called barren plateaus (BPs) phenomenon, where gradients of cost functions vanish exponentially with the number of qubits. In this paper, inspired by transfer learning, where knowledge of pre-solved tasks could be further used in a different but related work with training efficiency improved, we report a parameter initialization method to mitigate BP. In the method, a small-sized task is solved with a VQA. Then the ansatz and its optimum parameters are transferred to tasks with larger sizes. Numerical simulations show that this method could mitigate BP and improve training efficiency. A brief discussion on how this method can work well is also provided. This work provides a reference for mitigating BP, and therefore, VQAs could be applied to more practical problems.
Variational Quantum Algorithms (VQAs) are becoming the primary computational primitive for next-generation quantum computers, particularly those embedded as resource-constrained accelerators in the emerging Quantum Internet of Things (QIoT). However, under such device-constrained execution conditions, the scalability of learning is severely limited by barren plateaus, where gradients collapse to zero and training stalls. This poses a practical challenge to delivering VQA-enabled intelligence on QIoT endpoints, which often have few qubits, constrained shot budgets, and strict latency requirements. In this paper, we present a novel approach for escaping barren plateaus by including negative learning rates into the optimization process in QIoT devices. Our method introduces controlled instability into model training by switching between positive and negative learning phases, allowing recovery of significant gradients and exploring flatter areas in the loss landscape. We theoretically evaluate the effect of negative learning on gradient variance and propose conditions under which it helps escape from barren zones. The experimental findings on typical VQA benchmarks show consistent improvements in both convergence and simulation results over traditional optimizers. By escaping barren plateaus, our approach leads to a novel pathway for robust optimization in quantum-classical hybrid models.
Variational quantum algorithms face optimization difficulties due to barren plateaux, particularly as system size increases. In this work, we propose an evolutionary strategy–inspired approach that adaptively selects qubits for local cost evaluation and applies small perturbations to the selected parameters to optimize the local cost function. Numerical results on the identity gate learning problem indicate that adaptive qubit prioritization can reduce optimization stagnation and improve convergence behavior compared to standard global and local cost strategies. These findings suggest that evolutionary-guided control mechanisms may complement existing local-cost-based optimization methods in variational quantum algorithms.
One of the most important properties of classical neural networks is how surprisingly trainable they are, though their training algorithms typically rely on optimizing complicated, nonconvex loss functions. Previous results have shown that unlike the case in classical neural networks, variational quantum models are often not trainable. The most studied phenomenon is the onset of barren plateaus in the training landscape of these quantum models, typically when the models are very deep. This focus on barren plateaus has made the phenomenon almost synonymous with the trainability of quantum models. Here, we show that barren plateaus are only a part of the story. We prove that a wide class of variational quantum models-which are shallow, and exhibit no barren plateaus-have only a superpolynomially small fraction of local minima within any constant energy from the global minimum, rendering these models untrainable if no good initial guess of the optimal parameters is known. We also study the trainability of variational quantum algorithms from a statistical query framework, and show that noisy optimization of a wide variety of quantum models is impossible with a sub-exponential number of queries. Finally, we numerically confirm our results on a variety of problem instances. Though we exclude a wide variety of quantum algorithms here, we give reason for optimism for certain classes of variational algorithms and discuss potential ways forward in showing the practical utility of such algorithms.