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:2606.20183

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

Jian Xu, Delu Zeng, John Paisley, Qibin Zhao

Published Jun 18, 2026• 0 citations
arXivHTMLPDF

Abstract

Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the \emph{effective dimension} $d_{\rm eff}$ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move $d_{\rm eff}$; in an overfitting regime, contracting $d_{\rm eff}$ acts as ridge-like regularization. We analyze the mechanism: an \emph{exact} decomposition of the depolarized kernel $K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\top$ with $d_{\rm eff}(K_p)\to1$, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to $12$ qubits, not as evidence for $d_{\rm eff}$. Amplitude damping contracts $d_{\rm eff}$ and lifts test accuracy by up to $+13\%$ along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.

DOI
10.48550/arxiv.2606.20183

Related papers

Spectral Anatomy of Quantum Gaussian Process Kernels

Jian Xu, Chao Li, Guang Lin +4 more

Two recent results have reshaped quantum Gaussian processes (QGPs). On the one hand, \citet{lowe2025assessing} rule out the exponential speedups claimed by HHL-based QGP regression in the typical, well-conditioned regime; on the other, an independent line of work shows that highly expressive quantum kernels suffer posterior pathologies that break Bayesian optimization. We show that these seemingly unrelated phenomena are governed by the same quantity: the normalized spectral entropy $S(K)/\log n$ of the kernel Gram matrix. We prove a Cauchy--Schwarz tail bound on Nyström approximation error, a finite-sample variance-contraction identity in terms of Bach's degrees of freedom $d_σ(K)$, and a characterization of the \emph{target-dependent} optimal entropy via the intrinsic dimension of the target in the kernel eigenbasis. Empirically, the diagnostic is kernel-agnostic: hardware-efficient, matchgate, IQP \emph{and} RBF/Matérn/RFF/deep-kernel families all collapse onto identical $S/\log n$ curves on dequantization, ECE, and variance-contraction panels. The NLL sweet spot lives at high entropy for smooth targets and at low entropy for band-limited quantum-data targets. The diagnostic transfers from simulator to IBM Heron hardware with median absolute error $3.2\%$ and mean $5.2\%$ in $S/\log n$ across $24$ configurations at $n_q = 4$, with matchgate and IQP within $5\%$ mean and a single HE configuration returning a $30\%$ outlier that drops to $0.5\%$ on rerun (attributed to calibration drift); the same diagnostic transfers to a second Heron backend (mean error $2.7\%$) and to a $n_q = 6$ scale-up on the original backend (mean error $1.7\%$). No error mitigation is applied throughout.

arXiv:2605.30952•May 29, 2026•0 citations

Empirical Evaluation of Quantum Kernel Methods for Classification: A Comparative Study with Classical Kernels

Ronak Bhalgami

Quantum kernel methods are the most concrete near-term proposal for quantum machine learning on classical data, yet published benchmarks disagree on whether they outperform tuned classical kernels, and the disagreement cannot be resolved from the literature because the comparisons are not protocol-controlled. We argue that the obstacle is one of measurement, not theory: the usual setup fixes the quantum feature map's data scaling while grid-searching the classical kernel's hyperparameters, recomputes nothing per fold, and reports cost in simulator time. We therefore treat the comparison itself as the object of study and impose three controls. The bandwidth is tuned on the same grid budget as the classical $γ$, the kernel is recomputed inside every fold from fold-fitted preprocessing, and cost is counted in hardware circuit evaluations. On top of these we run a factorial design of 324 cells in which dimensionality, training size, class separability and data structure are explicit covariates, together with four standard datasets, a shots-versus-gate-noise ablation, and a cost sweep. The dominant effect we measure is not quantum: tuning the feature map's bandwidth is worth 0.120 accuracy on synthetic data and 0.339 on real data, exceeding every quantum-classical difference we observe. Tuned quantum kernels are then statistically indistinguishable from a tuned RBF on all four real datasets. The advantage on synthetic data is confined almost entirely to data generated by the feature map itself, and it shrinks with dimensionality (-0.0045 per qubit) while growing with sample size. Finite sampling costs an order of magnitude more accuracy than gate and readout noise, and a fidelity kernel needs $5\times10^{7}$ circuits at n = 10,000. Protocol variance is thus sufficient to explain the field's contradictory conclusions.

quant-pharXiv:2610.42029•Nov 2, 2026•0 citations

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification

Wang, Mingzhu, Shang, Yun

Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly distributed entanglement entropy consistently deliver superior non-local feature fusion and state-of-the-art accuracy (99.77% on CIFAR-10). Surprisingly, quantum noise emerges as a double-edged factor: in some cases, it enhances accuracy (+2.71% under amplitude damping). Strikingly, substituting the QCNN with classical counterparts of equal parameter count leads to a dramatic 29.36% drop, providing unambiguous evidence of quantum advantage. Our study establishes a principled pathway for co-designing classical and quantum architectures, pointing toward practical QML capable of tackling complex, high-dimensional learning tasks.

arXiv:2510.12291•Oct 14, 2025•1 citation

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

Complexity of tensor network simulation for noisy quantum circuits

Yuguo Shao, Zishuo Zhao, Song Cheng +1 more

We aim to rigorously address how local noise affects classical simulability of quantum dynamics benchmarked by tensor-network methods. Using operator entanglement entropy (OEE), we prove the following: (1) For single-qubit depolarizing noise on arbitrary circuits, tensor networks with $\mathrm{poly}(n)$ bond dimension suffice for fixed absolute Hilbert-Schmidt error after $\order{1}$ depth, while relative error demands $\order{\log n}$ depth; and this bound is optimal. (2) For single-qubit depolarizing noise on 1D local circuits, the existence of whole-trajectory error-bounded matrix product operator (MPO) of $\mathrm{poly}(n)$ bond dimension at all depths. (3) For general single-qubit noise in 1D brickwall circuits, random two-design gates with contraction coefficient $c<1/3$ yield an $\order{1}$ OEE plateau with probability $1-Te^{-Ω(n)}$, while arbitrary gates with $c<1/48$ give $\order{\log n}$ OEE in the worst case. (4) In higher dimensions, these bounds yield uniform-in-depth $\mathrm{poly}(n)$ average boundary-bond dimensions for projected entangled pair operators~(PEPO) across every cut -- under depolarizing noise at either absolute or relative accuracy, and under general noise with strong contraction at absolute accuracy. Our results establish a rigorous connection between certain noise models, circuit types, and their classical simulability.

cond-mat.str-elCross-listedarXiv:2606.00474•Jun 2, 2026•2 citations

Applicability of quantum-enhanced machine learning (本文)

ユウダイ スズキ, Yudai Suzuki, 雄大 鈴木

Quantum computers are next-generation computing devices that have the potential to enhance the performance of machine learning.An approach to achieving quantum enhancement is to utilize the Hilbert space, whose dimension scales exponentially in the number of qubits, as a feature space for machine learning.The use of such quantum-enhanced feature space could enable us to find data patterns more easily than conventional methods.Thus far, it has been theoretically shown that quantum-enhanced machine learning models can solve specific classification tasks that classical methods cannot efficiently solve.This motivates many researchers to pursue practical advantages of the methods.Toward practical applications, it is critical to establish guidelines for designs of quantum-enhanced machine learning models.This thesis aims to analyze the performance of quantum-enhanced machine learning models and give insights into design principles of the models for practical applications.More specifically, we focus on two methods, quantum kernel methods and quantum reservoir computing, and then provide guidelines for building their models in practical situations.We focus on two challenges in quantum kernel methods for real-world applications.The first is that constructing quantum feature maps is nontrivial when applied to actual machine learning problems.This thesis proposes a method for analyzing quantum feature maps, which can help screen a suitable quantum feature map among many candidates.In addition, we examine the effectiveness of a synthesis method to construct a powerful quantum kernel.Another issue is that implementation feasibility and trainability deteriorate as the number of qubits increases.We thus propose a new quantum kernel called the quantum Fisher kernel and demonstrate from analytical and numerical perspectives that our proposal can avoid the aforementioned problem when shallow alternating layered ansatzes are used.In quantum reservoir computing, there is room for investigation in designing quantum reservoir systems that are amenable to implementation and can perform well.In this thesis, we propose a quantum reservoir computing framework that positively makes use of unavoidable quantum noise in actual quantum hardware.Our experimental demonstrations on superconducting quantum devices show that quantum noise can enhance temporal information processing.Also, numerical analysis using a tool called temporal information processing capacity elucidates that dissipation noise such as amplitude damping can induce sequential data processing capabilities.

•Jan 1, 2023•0 citations
Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the \emph{effective dimension} deffd_{\rm eff}deff​ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move deffd_{\rm eff}deff​; in an overfitting regime, contracting deffd_{\rm eff}deff​ acts as ridge-like regularization. We analyze the mechanism: an \emph{exact} decomposition of the depolarized kernel Kp=(1−p)2K+p(2−p)D11⊤K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\topKp​=(1−p)2K+Dp(2−p)​11⊤ with deff(Kp)→1d_{\rm eff}(K_p)\to1deff​(Kp​)→1, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to 121212 qubits, not as evidence for deffd_{\rm eff}deff​. Amplitude damping contracts deffd_{\rm eff}deff​ and lifts test accuracy by up to +13%+13\%+13% along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.
Two recent results have reshaped quantum Gaussian processes (QGPs). On the one hand, \citet{lowe2025assessing} rule out the exponential speedups claimed by HHL-based QGP regression in the typical, well-conditioned regime; on the other, an independent line of work shows that highly expressive quantum kernels suffer posterior pathologies that break Bayesian optimization. We show that these seemingly unrelated phenomena are governed by the same quantity: the normalized spectral entropy S(K)/log⁡nS(K)/\log nS(K)/logn of the kernel Gram matrix. We prove a Cauchy--Schwarz tail bound on Nyström approximation error, a finite-sample variance-contraction identity in terms of Bach's degrees of freedom dσ(K)d_σ(K)dσ​(K), and a characterization of the \emph{target-dependent} optimal entropy via the intrinsic dimension of the target in the kernel eigenbasis. Empirically, the diagnostic is kernel-agnostic: hardware-efficient, matchgate, IQP \emph{and} RBF/Matérn/RFF/deep-kernel families all collapse onto identical S/log⁡nS/\log nS/logn curves on dequantization, ECE, and variance-contraction panels. The NLL sweet spot lives at high entropy for smooth targets and at low entropy for band-limited quantum-data targets. The diagnostic transfers from simulator to IBM Heron hardware with median absolute error 3.2%3.2\%3.2% and mean 5.2%5.2\%5.2% in S/log⁡nS/\log nS/logn across 242424 configurations at nq=4n_q = 4nq​=4, with matchgate and IQP within 5%5\%5% mean and a single HE configuration returning a 30%30\%30% outlier that drops to 0.5%0.5\%0.5% on rerun (attributed to calibration drift); the same diagnostic transfers to a second Heron backend (mean error 2.7%2.7\%2.7%) and to a nq=6n_q = 6nq​=6 scale-up on the original backend (mean error 1.7%1.7\%1.7%). No error mitigation is applied throughout.
Quantum kernel methods are the most concrete near-term proposal for quantum machine learning on classical data, yet published benchmarks disagree on whether they outperform tuned classical kernels, and the disagreement cannot be resolved from the literature because the comparisons are not protocol-controlled. We argue that the obstacle is one of measurement, not theory: the usual setup fixes the quantum feature map's data scaling while grid-searching the classical kernel's hyperparameters, recomputes nothing per fold, and reports cost in simulator time. We therefore treat the comparison itself as the object of study and impose three controls. The bandwidth is tuned on the same grid budget as the classical γγγ, the kernel is recomputed inside every fold from fold-fitted preprocessing, and cost is counted in hardware circuit evaluations. On top of these we run a factorial design of 324 cells in which dimensionality, training size, class separability and data structure are explicit covariates, together with four standard datasets, a shots-versus-gate-noise ablation, and a cost sweep. The dominant effect we measure is not quantum: tuning the feature map's bandwidth is worth 0.120 accuracy on synthetic data and 0.339 on real data, exceeding every quantum-classical difference we observe. Tuned quantum kernels are then statistically indistinguishable from a tuned RBF on all four real datasets. The advantage on synthetic data is confined almost entirely to data generated by the feature map itself, and it shrinks with dimensionality (-0.0045 per qubit) while growing with sample size. Finite sampling costs an order of magnitude more accuracy than gate and readout noise, and a fidelity kernel needs 5×1075\times10^{7}5×107 circuits at n = 10,000. Protocol variance is thus sufficient to explain the field's contradictory conclusions.
Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly distributed entanglement entropy consistently deliver superior non-local feature fusion and state-of-the-art accuracy (99.77% on CIFAR-10). Surprisingly, quantum noise emerges as a double-edged factor: in some cases, it enhances accuracy (+2.71% under amplitude damping). Strikingly, substituting the QCNN with classical counterparts of equal parameter count leads to a dramatic 29.36% drop, providing unambiguous evidence of quantum advantage. Our study establishes a principled pathway for co-designing classical and quantum architectures, pointing toward practical QML capable of tackling complex, high-dimensional learning tasks.
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.
We aim to rigorously address how local noise affects classical simulability of quantum dynamics benchmarked by tensor-network methods. Using operator entanglement entropy (OEE), we prove the following: (1) For single-qubit depolarizing noise on arbitrary circuits, tensor networks with poly(n)\mathrm{poly}(n)poly(n) bond dimension suffice for fixed absolute Hilbert-Schmidt error after $\order{1}$ depth, while relative error demands $\order{\log n}$ depth; and this bound is optimal. (2) For single-qubit depolarizing noise on 1D local circuits, the existence of whole-trajectory error-bounded matrix product operator (MPO) of poly(n)\mathrm{poly}(n)poly(n) bond dimension at all depths. (3) For general single-qubit noise in 1D brickwall circuits, random two-design gates with contraction coefficient c<1/3c<1/3c<1/3 yield an $\order{1}$ OEE plateau with probability 1−Te−Ω(n)1-Te^{-Ω(n)}1−Te−Ω(n), while arbitrary gates with c<1/48c<1/48c<1/48 give $\order{\log n}$ OEE in the worst case. (4) In higher dimensions, these bounds yield uniform-in-depth poly(n)\mathrm{poly}(n)poly(n) average boundary-bond dimensions for projected entangled pair operators~(PEPO) across every cut -- under depolarizing noise at either absolute or relative accuracy, and under general noise with strong contraction at absolute accuracy. Our results establish a rigorous connection between certain noise models, circuit types, and their classical simulability.
Quantum computers are next-generation computing devices that have the potential to enhance the performance of machine learning.An approach to achieving quantum enhancement is to utilize the Hilbert space, whose dimension scales exponentially in the number of qubits, as a feature space for machine learning.The use of such quantum-enhanced feature space could enable us to find data patterns more easily than conventional methods.Thus far, it has been theoretically shown that quantum-enhanced machine learning models can solve specific classification tasks that classical methods cannot efficiently solve.This motivates many researchers to pursue practical advantages of the methods.Toward practical applications, it is critical to establish guidelines for designs of quantum-enhanced machine learning models.This thesis aims to analyze the performance of quantum-enhanced machine learning models and give insights into design principles of the models for practical applications.More specifically, we focus on two methods, quantum kernel methods and quantum reservoir computing, and then provide guidelines for building their models in practical situations.We focus on two challenges in quantum kernel methods for real-world applications.The first is that constructing quantum feature maps is nontrivial when applied to actual machine learning problems.This thesis proposes a method for analyzing quantum feature maps, which can help screen a suitable quantum feature map among many candidates.In addition, we examine the effectiveness of a synthesis method to construct a powerful quantum kernel.Another issue is that implementation feasibility and trainability deteriorate as the number of qubits increases.We thus propose a new quantum kernel called the quantum Fisher kernel and demonstrate from analytical and numerical perspectives that our proposal can avoid the aforementioned problem when shallow alternating layered ansatzes are used.In quantum reservoir computing, there is room for investigation in designing quantum reservoir systems that are amenable to implementation and can perform well.In this thesis, we propose a quantum reservoir computing framework that positively makes use of unavoidable quantum noise in actual quantum hardware.Our experimental demonstrations on superconducting quantum devices show that quantum noise can enhance temporal information processing.Also, numerical analysis using a tool called temporal information processing capacity elucidates that dissipation noise such as amplitude damping can induce sequential data processing capabilities.