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:2503.22604

Enhanced Variational Quantum Kolmogorov-Arnold Network

Hikaru Wakaura, Rahmat Mulyawan, Andriyan Bayu Suksmono

Published Mar 28, 2025• 10 citations
arXivHTMLPDF

Abstract

The Kolmogorov-Arnold Network (KAN) places the trainable functions on the synapses rather than on the neurons. Existing quantum implementations either lack accuracy (Variational Quantum KAN, VQKAN) or rely on block encoding and Quantum Signal Processing, which demand many control gates and ancillae. We propose the Enhanced Variational Quantum Kolmogorov-Arnold Network (EVQKAN), a variational ansatz that emulates a $2^{N_q}$-dimensional KAN layer matrix by tiling controlled rotations through a sum-operator construction, using only $2^{N_q-1}$ trainable spline functions per layer. On the fitting of an elementary function, EVQKAN attains a significantly lower test error than Quantum Neural Networks (QNN), VQKAN and Adaptive VQKAN (Mann-Whitney $p<0.002$, Cliff's $δ\leq-0.86$ over ten attempts; EVQKAN beats VQKAN on every attempt), though classical KAN is more accurate still. On a two-dimensional classification task the ordering reverses: under a leak-free protocol introduced here, EVQKAN classifies above chance (accuracy $0.620$, $p=0.0005$) but is significantly less accurate than a QNN carrying one fifth as many parameters ($Δ$accuracy $-0.134$, $p=0.0014$; $Δ$AUC $-0.252$, $p=0.0002$). We withdraw the classification results of an earlier version of this work: their encoding placed the target label into the circuit as a feature for EVQKAN but not for the methods it was compared against. The dominant error source is overfitting from an under-determined training set; enlarging that set closes the train-test gap by $58\%$ (Spearman $p<10^{-3}$). We also report the circuit cost in full --- three layers emit $1017$ operations, or $4110$ two-qubit gates once the multi-controlled gates are decomposed --- so the construction is simulator-scale and fault-tolerant-era rather than NISQ-ready, with block encoding and qubitization the route to reducing it.

DOI
10.48550/arxiv.2503.22604

Related papers

Variational quantum Kolmogorov–Arnold network

Hikaru Wakaura, Rahmat Mulyawan, Andriyan Bayu Suksmono

Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for the fitting of the given function in various ways, such as by using ansatzes and comparisons.

Quantum Information Processing•Aug 10, 2026•0 citations

The quantum version of Kolmogorov-Arnold Network ( KAN ) : Variational Quantum Kolmogorov-Arnold Network.

Hikaru Wakaura, Andriyan Bayu Suksmono

Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for the fitting of the given function in some ways, such as by using ansatzes and comparisons.

•Jun 3, 2024•1 citation

Variational Quantum Kolmogorov-Arnold Network

Hikaru Wakaura, Andriyan Bayu Suksmono, Rahmat Mulyawan

Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for fitting the given function in various ways, such as by using ansatzes and comparisons.

•Dec 26, 2024•2 citations

Variational Quantum Kolmogorov-Arnold Network

Hikaru Wakaura, Andriyan Bayu Suksmono, Rahmat Mulyawan

Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for fitting the given function in various ways, such as by using ansatzes and comparisons.

•Jul 19, 2024•9 citations

Quantum Kolmogorov--Arnold networks are classically reproducible at their attained accuracy, and a discrete-logarithm encoding need not be: a measurement-based map of where quantum advantage can live

Hikaru Wakaura

Abstract Quantum machine-learning models are useful only if classical computers cannot cheaply imitate them. We test this directly for quantum Kolmogorov--Arnold networks (QKANs)---neural networks whose tunable ``activation functions'' are small quantum circuits---by asking whether each model can be contracted as an efficient tensor network (TN). Our task-aware yardstick is the bond dimension a classical surrogate needs to copy the model's output at the accuracy the model itself reaches. We find a clear ladder. The amplitude-encoded Chebyshev QKAN uses only logarithmically many qubits and is exactly classical. The variational QKAN, built from all-to-all controlled rotations, looks hard at random settings but generalizes only weakly once trained (held-out $R^2\!\le\!0.27$) and is copied at that attained accuracy by a low-bond-dimension surrogate ($n\!\le\!10$); at fixed strict tolerance the required bond dimension grows near-exponentially. Depolarizing noise erases it (purity collapse) near $p\!\approx\!0.03$--$0.05$ at the sizes we reach. Every generic attempt to force hardness---a global measurement or an interaction-based (IQP) feature map---instead destroys trainability through exponentially small gradients (a ``barren plateau''). The escape is a discrete-logarithm feature map: its kernel variance is flat from $4$ to $14$ qubits while a generic IQP kernel concentrates exponentially, and a support-vector machine with it learns a classically hard concept to $\ge99\%$ accuracy while generic and classical kernels stay at chance; wired into the KAN architecture, it fits discrete-log targets to $R^2\!\approx\!1$. Hardness placed in number theory stays classically hard, shot-efficient, and learnable. The work provides a measurement-based reproducibility criterion and a design rule: seek advantage in structured, provably hard encodings rather than in deep entanglement.

•Oct 20, 2026•0 citations

Few-sample regression with an adaptively grown variational quantum Kolmogorov--Arnold network

Hikaru Wakaura, Rahmat Mulyawan, Andriyan Bayu Suksmono

Kolmogorov-Arnold networks place learnable one-dimensional functions on the edges of a network rather than fixed activations on its nodes, and several quantum realisations have been proposed. Whether any of them offers a practical benefit is unclear, because the reported comparisons rest on single training runs, untuned baselines, and test sets that were also used for model selection. Here we evaluate a variational quantum Kolmogorov-Arnold network whose ansatz is grown one Pauli operator at a time, under a protocol with seed-paired comparisons, a stopping rule that never sees the test set, and a confirmatory study whose hypotheses, seeds, and analysis were committed before the runs. On four-qubit benchmarks the model is indistinguishable from a quantum neural network of the same parameter count and is outperformed by classical regressors. On a difficulty-controlled family of 12- and 16-dimensional targets learned from ten training points, the 32-parameter quantum model beats the best of four unregularised classical regressors and a tuned quantum neural network with Holm-corrected p <= 0.017; the result is unchanged with 256 measurement shots per circuit, and the trained models run on a 156-qubit IBM processor with test errors within 0.3 of the exact values. A kernel ridge regressor with hyperparameters chosen by leave-one-out cross-validation on the same ten points matches the quantum model, and a sample-size sweep shows that the quantum model's error is nearly flat in the training-set size while the classical models keep improving. The benefit of the quantum model is therefore an implicit regularisation of a low-capacity model, present only in the few-sample regime and absent at 18 dimensions, not an expressivity advantage. These results give a reproducible reference point for the resources and limits of variational quantum Kolmogorov-Arnold networks.

arXiv:2503.21336•Mar 27, 2025•7 citations
The Kolmogorov-Arnold Network (KAN) places the trainable functions on the synapses rather than on the neurons. Existing quantum implementations either lack accuracy (Variational Quantum KAN, VQKAN) or rely on block encoding and Quantum Signal Processing, which demand many control gates and ancillae. We propose the Enhanced Variational Quantum Kolmogorov-Arnold Network (EVQKAN), a variational ansatz that emulates a 2Nq2^{N_q}2Nq​-dimensional KAN layer matrix by tiling controlled rotations through a sum-operator construction, using only 2Nq−12^{N_q-1}2Nq​−1 trainable spline functions per layer. On the fitting of an elementary function, EVQKAN attains a significantly lower test error than Quantum Neural Networks (QNN), VQKAN and Adaptive VQKAN (Mann-Whitney p<0.002p<0.002p<0.002, Cliff's δ≤−0.86δ\leq-0.86δ≤−0.86 over ten attempts; EVQKAN beats VQKAN on every attempt), though classical KAN is more accurate still. On a two-dimensional classification task the ordering reverses: under a leak-free protocol introduced here, EVQKAN classifies above chance (accuracy 0.6200.6200.620, p=0.0005p=0.0005p=0.0005) but is significantly less accurate than a QNN carrying one fifth as many parameters (ΔΔΔaccuracy −0.134-0.134−0.134, p=0.0014p=0.0014p=0.0014; ΔΔΔAUC −0.252-0.252−0.252, p=0.0002p=0.0002p=0.0002). We withdraw the classification results of an earlier version of this work: their encoding placed the target label into the circuit as a feature for EVQKAN but not for the methods it was compared against. The dominant error source is overfitting from an under-determined training set; enlarging that set closes the train-test gap by 58%58\%58% (Spearman p<10−3p<10^{-3}p<10−3). We also report the circuit cost in full --- three layers emit 101710171017 operations, or 411041104110 two-qubit gates once the multi-controlled gates are decomposed --- so the construction is simulator-scale and fault-tolerant-era rather than NISQ-ready, with block encoding and qubitization the route to reducing it.
Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for the fitting of the given function in various ways, such as by using ansatzes and comparisons.
Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for the fitting of the given function in some ways, such as by using ansatzes and comparisons.
Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for fitting the given function in various ways, such as by using ansatzes and comparisons.
Abstract We implemented a quantum version of the Kolmogorov-Arnold Network (KAN) on a quantum circuit. It optimizes the weight of each synaptic connection to enhance the overall performance of the neurons. This approach offers a significant boost in efficiency over traditional neural networks, as it can be optimized more accurately and requires only a few neurons to solve complex problems. The KAN is a multi-layer network, similar to a traditional neural network, with each layer represented as a matrix containing parameters and feedback. This structure is linear and mirrors the form of Variational Quantum Algorithms. Thus, we propose the Variational Quantum Kolmogorov-Arnold Network (VQKAN) as a quantum version of the Kolmogorov-Arnold Network. We demonstrated the optimization of VQKAN for fitting the given function in various ways, such as by using ansatzes and comparisons.
Abstract Quantum machine-learning models are useful only if classical computers cannot cheaply imitate them. We test this directly for quantum Kolmogorov--Arnold networks (QKANs)---neural networks whose tunable ``activation functions'' are small quantum circuits---by asking whether each model can be contracted as an efficient tensor network (TN). Our task-aware yardstick is the bond dimension a classical surrogate needs to copy the model's output at the accuracy the model itself reaches. We find a clear ladder. The amplitude-encoded Chebyshev QKAN uses only logarithmically many qubits and is exactly classical. The variational QKAN, built from all-to-all controlled rotations, looks hard at random settings but generalizes only weakly once trained (held-out R2 ⁣≤ ⁣0.27R^2\!\le\!0.27R2≤0.27) and is copied at that attained accuracy by a low-bond-dimension surrogate (n ⁣≤ ⁣10n\!\le\!10n≤10); at fixed strict tolerance the required bond dimension grows near-exponentially. Depolarizing noise erases it (purity collapse) near p ⁣≈ ⁣0.03p\!\approx\!0.03p≈0.03--0.050.050.05 at the sizes we reach. Every generic attempt to force hardness---a global measurement or an interaction-based (IQP) feature map---instead destroys trainability through exponentially small gradients (a ``barren plateau''). The escape is a discrete-logarithm feature map: its kernel variance is flat from 444 to 141414 qubits while a generic IQP kernel concentrates exponentially, and a support-vector machine with it learns a classically hard concept to ≥99%\ge99\%≥99% accuracy while generic and classical kernels stay at chance; wired into the KAN architecture, it fits discrete-log targets to R2 ⁣≈ ⁣1R^2\!\approx\!1R2≈1. Hardness placed in number theory stays classically hard, shot-efficient, and learnable. The work provides a measurement-based reproducibility criterion and a design rule: seek advantage in structured, provably hard encodings rather than in deep entanglement.
Kolmogorov-Arnold networks place learnable one-dimensional functions on the edges of a network rather than fixed activations on its nodes, and several quantum realisations have been proposed. Whether any of them offers a practical benefit is unclear, because the reported comparisons rest on single training runs, untuned baselines, and test sets that were also used for model selection. Here we evaluate a variational quantum Kolmogorov-Arnold network whose ansatz is grown one Pauli operator at a time, under a protocol with seed-paired comparisons, a stopping rule that never sees the test set, and a confirmatory study whose hypotheses, seeds, and analysis were committed before the runs. On four-qubit benchmarks the model is indistinguishable from a quantum neural network of the same parameter count and is outperformed by classical regressors. On a difficulty-controlled family of 12- and 16-dimensional targets learned from ten training points, the 32-parameter quantum model beats the best of four unregularised classical regressors and a tuned quantum neural network with Holm-corrected p <= 0.017; the result is unchanged with 256 measurement shots per circuit, and the trained models run on a 156-qubit IBM processor with test errors within 0.3 of the exact values. A kernel ridge regressor with hyperparameters chosen by leave-one-out cross-validation on the same ten points matches the quantum model, and a sample-size sweep shows that the quantum model's error is nearly flat in the training-set size while the classical models keep improving. The benefit of the quantum model is therefore an implicit regularisation of a low-capacity model, present only in the few-sample regime and absent at 18 dimensions, not an expressivity advantage. These results give a reproducible reference point for the resources and limits of variational quantum Kolmogorov-Arnold networks.