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:2604.02064

Quantitative Universal Approximation for Noisy Quantum Neural Networks

Lukas Gonon, Antoine Jacquier, Marcel Mordarski

quant-phmath.NAq-fin.PRSubmitted Apr 2, 2026• Announced Apr 3, 2026• 0 citations• Revised Apr 4, 2026 (v2)
v1 · Apr 2, 2026v2 · Apr 4, 2026v3 · May 19, 2026
arXivHTMLPDF

Abstract

We provide here a universal approximation theorem with precise quantitative error bounds for noisy quantum neural networks. We focus on applications to Quantitative Finance, where target functions are often given as expectations. We further provide a detailed numerical analysis, testing our results on actual noisy quantum hardware.
Comments
30 pages, 17 figures

Related papers

Universal Approximation Theorem and Error Bounds for Quantum Neural Networks and Quantum Reservoirs

Lukas Gonon, Antoine Jacquier

Universal approximation theorems are the foundations of classical neural networks, providing theoretical guarantees that the latter are able to approximate maps of interest. Recent results have shown that this can also be achieved in a quantum setting, whereby classical functions can be approximated by parameterized quantum circuits. We provide here precise error bounds for specific classes of functions and extend these results to the interesting new setup of randomized quantum circuits, mimicking classical reservoir neural networks. Our results show in particular that a quantum neural network with ${\mathcal {O}}(\varepsilon ^{-2})$ weights and ${\mathcal {O}} (\lceil \log _{2}(\varepsilon ^{-1})\rceil)$ qubits suffices to achieve approximation error $\varepsilon \gt 0$ when approximating functions with integrable Fourier transforms.

arXiv:2307.12904•IEEE Transactions on Neural Networks and Learning Systems•Apr 9, 2025•9 citations

Expressivity of quantum neural networks

Yadong Wu, Juan Yao, Pengfei Zhang +1 more

In this work, we address the question whether a sufficiently deep quantum neural network can approximate a target function as accurate as possible. We start with simple but typical physical situations that the target functions are physical observables, and then we extend our discussion to situations that the learning targets are not directly physical observables, but can be expressed as physical observables in an enlarged Hilbert space with multiple replicas, such as the Loshimidt echo and the Renyi entropy. The main finding is that an accurate approximation is possible only when the input wave functions in the dataset do not exhaust the entire Hilbert space that the quantum circuit acts on, and more precisely, the Hilbert space dimension of the former has to be less than half of the Hilbert space dimension of the latter. In some cases, this requirement can be satisfied automatically because of the intrinsic properties of the dataset, for instance, when the input wave function has to be symmetric between different replicas. And if this requirement cannot be satisfied by the dataset, we show that the expressivity capabilities can be restored by adding one ancillary qubit where the wave function is always fixed at input. Our studies point toward establishing a quantum neural network analogy of the universal approximation theorem that lays the foundation for expressivity of classical neural networks.

arXiv:2101.04273•Physical Review Research•Aug 23, 2021•49 citations

Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits

Zhan Yu, Qiuhao Chen, Yuling Jiao +4 more

Parameterized quantum circuits (PQCs) have emerged as a promising approach for quantum neural networks. However, understanding their expressive power in accomplishing machine learning tasks remains a crucial question. This paper investigates the expressivity of PQCs for approximating general multivariate function classes. Unlike previous Universal Approximation Theorems for PQCs, which are either nonconstructive or rely on parameterized classical data processing, we explicitly construct data re-uploading PQCs for approximating multivariate polynomials and smooth functions. We establish the first non-asymptotic approximation error bounds for these functions in terms of the number of qubits, quantum circuit depth, and number of trainable parameters. Notably, we demonstrate that for approximating functions that satisfy specific smoothness criteria, the quantum circuit size and number of trainable parameters of our proposed PQCs can be smaller than those of deep ReLU neural networks. We further validate the approximation capability of PQCs through numerical experiments. Our results provide a theoretical foundation for designing practical PQCs and quantum neural networks for machine learning tasks that can be implemented on near-term quantum devices, paving the way for the advancement of quantum machine learning.

arXiv:2310.07528•neural information processing systems•Jan 1, 2024•4 citations

Evaluating the performance of sigmoid quantum perceptrons in quantum neural networks

Samuel A. Wilkinson, Michael J. Hartmann

Quantum neural networks (QNN) have been proposed as a promising architecture for quantum machine learning. There exist a number of different quantum circuit designs being branded as QNNs, however no clear candidate has presented itself as more suitable than the others. Rather, the search for a ``quantum perceptron" -- the fundamental building block of a QNN -- is still underway. One candidate is quantum perceptrons designed to emulate the nonlinear activation functions of classical perceptrons. Such sigmoid quantum perceptrons (SQPs) inherit the universal approximation property that guarantees that classical neural networks can approximate any function. However, this does not guarantee that QNNs built from SQPs will have any quantum advantage over their classical counterparts. Here we critically investigate both the capabilities and performance of SQP networks by computing their effective dimension and effective capacity, as well as examining their performance on real learning problems. The results are compared to those obtained for other candidate networks which lack activation functions. It is found that simpler, and apparently easier-to-implement parametric quantum circuits actually perform better than SQPs. This indicates that the universal approximation theorem, which a cornerstone of the theory of classical neural networks, is not a relevant criterion for QNNs.

arXiv:2208.06198•Aug 12, 2022•4 citations

On the Universal Approximability and Complexity Bounds of Deep Learning in Hybrid Quantum-Classical Computing

Weiwen Jiang, Yukun Ding, Yiyu Shi

With the continuously increasing number of quantum bits in quantum computers, there are growing interests in exploring applications that can harvest the power of them. Recently, several attempts were made to implement neural networks, known to be computationally intensive, in hybrid quantum-classical scheme computing. While encouraging results are shown, two fundamental questions need to be answered: (1) whether neural networks in hybrid quantum-classical computing can leverage quantum power and meanwhile approximate any function within a given error bound, i.e., universal approximability; (2) how do these neural networks compare with ones on a classical computer in terms of representation power? This work sheds light on these two questions from a theoretical perspective.

•May 4, 2021•0 citations

A universal duplication-free quantum neural network

Xiaokai Hou, Guanyu Zhou, Qingyu Li +2 more

Universality of neural networks describes the ability to approximate arbitrary function, and is a key ingredient to keep the method effective. The established models for universal quantum neural networks(QNN), however, require the preparation of multiple copies of the same quantum state to generate the nonlinearity, with the copy number increasing significantly for highly oscillating functions, resulting in a huge demand for a large-scale quantum processor. To address this problem, we propose a new QNN model that harbors universality without the need of multiple state-duplications, and is more likely to get implemented on near-term devices. To demonstrate the effectiveness, we compare our proposal with two popular QNN models in solving typical supervised learning problems. We find that our model requires significantly fewer qubits and it outperforms the other two in terms of accuracy and relative error.

arXiv:2106.13211•Jun 24, 2021•2 citations
Universal approximation theorems are the foundations of classical neural networks, providing theoretical guarantees that the latter are able to approximate maps of interest. Recent results have shown that this can also be achieved in a quantum setting, whereby classical functions can be approximated by parameterized quantum circuits. We provide here precise error bounds for specific classes of functions and extend these results to the interesting new setup of randomized quantum circuits, mimicking classical reservoir neural networks. Our results show in particular that a quantum neural network with O(ε−2){\mathcal {O}}(\varepsilon ^{-2})O(ε−2) weights and O(⌈log⁡2(ε−1)⌉){\mathcal {O}} (\lceil \log _{2}(\varepsilon ^{-1})\rceil)O(⌈log2​(ε−1)⌉) qubits suffices to achieve approximation error ε>0\varepsilon \gt 0ε>0 when approximating functions with integrable Fourier transforms.
In this work, we address the question whether a sufficiently deep quantum neural network can approximate a target function as accurate as possible. We start with simple but typical physical situations that the target functions are physical observables, and then we extend our discussion to situations that the learning targets are not directly physical observables, but can be expressed as physical observables in an enlarged Hilbert space with multiple replicas, such as the Loshimidt echo and the Renyi entropy. The main finding is that an accurate approximation is possible only when the input wave functions in the dataset do not exhaust the entire Hilbert space that the quantum circuit acts on, and more precisely, the Hilbert space dimension of the former has to be less than half of the Hilbert space dimension of the latter. In some cases, this requirement can be satisfied automatically because of the intrinsic properties of the dataset, for instance, when the input wave function has to be symmetric between different replicas. And if this requirement cannot be satisfied by the dataset, we show that the expressivity capabilities can be restored by adding one ancillary qubit where the wave function is always fixed at input. Our studies point toward establishing a quantum neural network analogy of the universal approximation theorem that lays the foundation for expressivity of classical neural networks.
Parameterized quantum circuits (PQCs) have emerged as a promising approach for quantum neural networks. However, understanding their expressive power in accomplishing machine learning tasks remains a crucial question. This paper investigates the expressivity of PQCs for approximating general multivariate function classes. Unlike previous Universal Approximation Theorems for PQCs, which are either nonconstructive or rely on parameterized classical data processing, we explicitly construct data re-uploading PQCs for approximating multivariate polynomials and smooth functions. We establish the first non-asymptotic approximation error bounds for these functions in terms of the number of qubits, quantum circuit depth, and number of trainable parameters. Notably, we demonstrate that for approximating functions that satisfy specific smoothness criteria, the quantum circuit size and number of trainable parameters of our proposed PQCs can be smaller than those of deep ReLU neural networks. We further validate the approximation capability of PQCs through numerical experiments. Our results provide a theoretical foundation for designing practical PQCs and quantum neural networks for machine learning tasks that can be implemented on near-term quantum devices, paving the way for the advancement of quantum machine learning.
Quantum neural networks (QNN) have been proposed as a promising architecture for quantum machine learning. There exist a number of different quantum circuit designs being branded as QNNs, however no clear candidate has presented itself as more suitable than the others. Rather, the search for a ``quantum perceptron" -- the fundamental building block of a QNN -- is still underway. One candidate is quantum perceptrons designed to emulate the nonlinear activation functions of classical perceptrons. Such sigmoid quantum perceptrons (SQPs) inherit the universal approximation property that guarantees that classical neural networks can approximate any function. However, this does not guarantee that QNNs built from SQPs will have any quantum advantage over their classical counterparts. Here we critically investigate both the capabilities and performance of SQP networks by computing their effective dimension and effective capacity, as well as examining their performance on real learning problems. The results are compared to those obtained for other candidate networks which lack activation functions. It is found that simpler, and apparently easier-to-implement parametric quantum circuits actually perform better than SQPs. This indicates that the universal approximation theorem, which a cornerstone of the theory of classical neural networks, is not a relevant criterion for QNNs.
With the continuously increasing number of quantum bits in quantum computers, there are growing interests in exploring applications that can harvest the power of them. Recently, several attempts were made to implement neural networks, known to be computationally intensive, in hybrid quantum-classical scheme computing. While encouraging results are shown, two fundamental questions need to be answered: (1) whether neural networks in hybrid quantum-classical computing can leverage quantum power and meanwhile approximate any function within a given error bound, i.e., universal approximability; (2) how do these neural networks compare with ones on a classical computer in terms of representation power? This work sheds light on these two questions from a theoretical perspective.
Universality of neural networks describes the ability to approximate arbitrary function, and is a key ingredient to keep the method effective. The established models for universal quantum neural networks(QNN), however, require the preparation of multiple copies of the same quantum state to generate the nonlinearity, with the copy number increasing significantly for highly oscillating functions, resulting in a huge demand for a large-scale quantum processor. To address this problem, we propose a new QNN model that harbors universality without the need of multiple state-duplications, and is more likely to get implemented on near-term devices. To demonstrate the effectiveness, we compare our proposal with two popular QNN models in solving typical supervised learning problems. We find that our model requires significantly fewer qubits and it outperforms the other two in terms of accuracy and relative error.