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

Journal of Applied Physics

Quantum algorithm for low-rank matrix regression with feature extraction

Kaitian Gao, Youlong Yang, Zhenye Du

Published Jan 5, 2026• 0 citations
Publisher

Abstract

Low-rank matrix regression is a pivotal technique in image processing and pattern recognition that can directly handle data with intrinsic matrix structures. However, classical algorithms for this task suffer from a computational bottleneck, where the complexity escalates cubically with the matrix dimension, incurring prohibitive costs for high-dimensional datasets. In this study, we propose a quantum algorithm for low-rank matrix regression with feature extraction, leveraging the Harrow–Hassidim–Lloyd algorithm for regression matrix estimation and a modified quantum singular-value thresholding algorithm for iterative variable updates. Theoretical analysis demonstrates that our algorithm reduces the time complexity dependence on the matrix dimension from cubic to logarithmic, achieving an exponential speedup over classical counterparts when the problem is well conditioned and the precision requirements are moderate. Furthermore, we introduce an algorithmic variant utilizing the quantum memory model to bypass the reliance on quantum random access memory. Additionally, we propose a hybrid strategy leveraging quantum sketching techniques to effectively eliminate the runtime dependence on the condition number. Subsequently, we performed small-scale quantum experiments to validate the feasibility of our proposed quantum algorithm.

DOI
10.1063/5.0297644

Related papers

An improved quantum-inspired algorithm for linear regression

András Gilyén, Zhao Song, Ewin Tang

We give a classical algorithm for linear regression analogous to the quantum matrix inversion algorithm [Harrow, Hassidim, and Lloyd, Physical Review Letters'09] for low-rank matrices [Wossnig, Zhao, and Prakash, Physical Review Letters'18], when the input matrix A is stored in a data structure applicable for QRAM-based state preparation.Namely, suppose we are given an A∈Cm×n with minimum non-zero singular value σ which supports certain efficient ℓ2 -norm importance sampling queries, along with a b∈Cm . Then, for some x∈Cn satisfying ‖x–A+b‖≤ε‖A+b‖ , we can output a measurement of |x⟩ in the computational basis and output an entry of x with classical algorithms that run in O~(‖A‖F6‖A‖6σ12ε4) and O~(‖A‖F6‖A‖2σ8ε4) time, respectively. This improves on previous "quantum-inspired" algorithms in this line of research by at least a factor of ‖A‖16σ16ε2 [Chia, Gilyén, Li, Lin, Tang, and Wang, STOC'20]. As a consequence, we show that quantum computers can achieve at most a factor-of-12 speedup for linear regression in this QRAM data structure setting and related settings. Our work applies techniques from sketching algorithms and optimization to the quantum-inspired literature. Unlike earlier works, this is a promising avenue that could lead to feasible implementations of classical regression in a quantum-inspired settings, for comparison against future quantum computers.

arXiv:2009.07268•Quantum•Jun 30, 2022•72 citations

Quantum algorithm for support matrix machines

Bojia Duan, Jiabin Yuan, Ying Liu +1 more

We propose a quantum algorithm for support matrix machines (SMMs) that efficiently addresses an image classification problem by introducing a least-squares reformulation. This algorithm consists of two core subroutines: a quantum matrix inversion (Harrow-Hassidim-Lloyd, HHL) algorithm and a quantum singular value thresholding (QSVT) algorithm. The two algorithms can be implemented on a universal quantum computer with complexity $O\left[log\left(npq\right)\right]$ and $O\left[log\left(pq\right)\right]$, respectively, where $n$ is the number of the training data and $pq$ is the size of the feature space. By iterating the algorithms, we can find the parameters for the SMM classfication model. Our analysis shows that both HHL and QSVT algorithms achieve an exponential increase of speed over their classical counterparts.

Physical Review A•Sep 1, 2017•65 citations

Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimension

András Gilyén, Seth Lloyd, Ewin Tang

We construct an efficient classical analogue of the quantum matrix inversion algorithm (HHL) for low-rank matrices. Inspired by recent work of Tang, assuming length-square sampling access to input data, we implement the pseudoinverse of a low-rank matrix and sample from the solution to the problem $Ax=b$ using fast sampling techniques. We implement the pseudo-inverse by finding an approximate singular value decomposition of $A$ via subsampling, then inverting the singular values. In principle, the approach can also be used to apply any desired "smooth" function to the singular values. Since many quantum algorithms can be expressed as a singular value transformation problem, our result suggests that more low-rank quantum algorithms can be effectively "dequantised" into classical length-square sampling algorithms.

arXiv:1811.04909•Nov 12, 2018•130 citations

Continuous-variable quantum Gaussian process regression and quantum singular value decomposition of nonsparse low-rank matrices

Siddhartha Das, George Siopsis, Christian Weedbrook

With the significant advancement in quantum computation during the past couple of decades, the exploration of machine-learning subroutines using quantum strategies has become increasingly popular. Gaussian process regression is a widely used technique in supervised classical machine learning. Here we introduce an algorithm for Gaussian process regression using continuous-variable quantum systems that can be realized with technology based on photonic quantum computers under certain assumptions regarding distribution of data and availability of efficient quantum access. Our algorithm shows that by using a continuous-variable quantum computer a dramatic speedup in computing Gaussian process regression can be achieved, i.e., the possibility of exponentially reducing the time to compute. Furthermore, our results also include a continuous-variable quantum-assisted singular value decomposition method of nonsparse low rank matrices and forms an important subroutine in our Gaussian process regression algorithm.

arXiv:1707.00360•Physical Review A•Feb 12, 2018•29 citations

Quantum Algorithms for Linear Algebra and Machine Learning.

Anupam Prakash

Most quantum algorithms offering speedups over classical algorithms are based on the three techniques of phase estimation, amplitude estimation and Hamiltonian simulation. In spite of the linear algebraic nature of the postulates of quantum mechanics, until recent work by Lloyd and coauthors cite{LMR13, LMR13a, LMR13b} no quantum algorithms achieving speedups for linear algebra or machine learning had been proposed. A quantum machine learning algorithm must address three issues: encoding of classical data into a succinct quantum representation, processing the quantum representation and extraction of classically useful information from the processed quantum state. In this dissertation, we make progress on all three aspects of the quantum machine learning problem and obtain quantum algorithms for low rank approximation and regularized least squares. The oracle $QRAM$, the standard model studied in quantum query complexity, requires time $O(sqrt{n})$ to encode vectors $v in R^{n}$ into quantum states. We propose simple hardware augmentations to the oracle $QRAM$, that enable vectors $v in R^{n}$ to be encoded in time $O(log n)$, with pre-processing. The augmented $QRAM$ incurs minimal hardware overheads, the pre-processing can be parallelized and is a flexible model that allows storage of multiple vectors and matrices. It provides a framework for designing quantum algorithms for linear algebra and machine learning. Using the augmented $QRAM$ for vector state preparation, we present two different algorithms for singular value estimation where given singular vector $ket{v}$ for $A in R^{mtimes n}$, the singular value $sigma_{i}$ is estimated within additive error $epsilon norm{A}_{F}$. The first algorithm requires time $wt{1/epsilon^{3}}$ and uses the approach for simulating $e^{-i rho}$ in cite{LMR13}. However, the analysis cite{LMR13} does not establish the coherence of outputs, we provide a qualitatively different analysis that uses the quantum Zeno effect to establish coherence and reveals the probabilistic nature of the simulation technique. The second algorithm has a running time $wt{1/epsilon}$ and uses Jordan's lemma from linear algebra and the augmented $QRAM$ to implement reflections. We use quantum singular value estimation to obtain algorithms for low rank approximation by column selection, the algorithms are based on importance sampling from the leverage score distribution. We obtain quadratic speedups for a large class of linear algebra algorithms that rely on importance sampling from the leverage score distribution including approximate least squares and $CX$ and $CUR$ decompositions. Classical algorithms for these problems require time $O(mn log n + poly(1/epsilon))$, the quantum algorithms have running time $O(sqrt{m}poly(1/epsilon, k, Delta))$ where $k, Delta$ are the rank and spectral gap. The running time of the quantum $CX$ decomposition algorithm does not depend on $m$, it is polynomial in problem parameters. We also provide quantum algorithms for $ell_{2}$ regularized regression problems, the quantum ridge regression algorithm requires time $wt{1/mu^{2} delta}$ to output a quantum state that is $delta$ close to the solution, where $mu$ is the regularization parameter.

•Jan 1, 2014•51 citations

Quantum Algorithms for Matrix Problems and Machine Learning

Sathyawageeswar Subramanian

This dissertation presents a study of quantum algorithms for problems that can be posed as matrix function tasks. In Chapter 1 we demonstrate a simple unifying framework for implementing of smooth functions of matrices on a quantum computer. This framework captures a variety of problems that can be solved by evaluating properties of some function of a matrix, and we identify speedups over classical algorithms for some problem classes. The analysis combines ideas from the classical theory of function approximation with the quantum algorithmic primitive of implementing linear combinations of unitary operators. In Chapter 2 we continue this study by looking at the role of sparsity of input matrices in constructing efficient quantum algorithms. We show that classically pre-processing an input matrix by spectral sparsification can be profitable for quantum Hamiltonian simulation algorithms, without compromising the simulation error or complexity. Such preprocessing incurs a one time cost linear in the size of the matrix, but can be exploited to exponentially speed up subsequent subroutines such as inversion. In Chapter 3, we give an application of this theory of matrix functions to the problem of estimating the Renyi entropy of an unknown quantum state. We combine matrix function techniques with mixed state quantum computation in the one-clean qubit model, and are able to bound of the expected runtime of our algorithm in terms of the unknown target quantity. In addition to the theme of analysing the complexity of our algorithms, we also identify instances that are of practical relevance, leading us to some problems of machine learning. In Chapter 4 we investigate kernel based learning methods using random features. We work with the QRAM input model suitable for big data, and show how matrix functions and the quantum Fourier transform can be used to devise a quantum algorithm for sampling random features that are optimised for given input data and choice of kernel. We obtain a potential exponential speedup over the best known classical algorithm even without explicit assumptions of sparsity or low rank. Finally in Chapter 5 we consider the technique of beamsearch decoding used in natural language processing. We work in the query model, and show how quantum search with advice can be used to construct a quantum search decoder that can find the optimal parse (which may for instance be a best translation, or text-to-speech transcript) at least quadratically faster than the best known classical algorithms, and obtain super-quadratic speedups in the expected runtime.

•Jul 24, 2020•0 citations
Low-rank matrix regression is a pivotal technique in image processing and pattern recognition that can directly handle data with intrinsic matrix structures. However, classical algorithms for this task suffer from a computational bottleneck, where the complexity escalates cubically with the matrix dimension, incurring prohibitive costs for high-dimensional datasets. In this study, we propose a quantum algorithm for low-rank matrix regression with feature extraction, leveraging the Harrow–Hassidim–Lloyd algorithm for regression matrix estimation and a modified quantum singular-value thresholding algorithm for iterative variable updates. Theoretical analysis demonstrates that our algorithm reduces the time complexity dependence on the matrix dimension from cubic to logarithmic, achieving an exponential speedup over classical counterparts when the problem is well conditioned and the precision requirements are moderate. Furthermore, we introduce an algorithmic variant utilizing the quantum memory model to bypass the reliance on quantum random access memory. Additionally, we propose a hybrid strategy leveraging quantum sketching techniques to effectively eliminate the runtime dependence on the condition number. Subsequently, we performed small-scale quantum experiments to validate the feasibility of our proposed quantum algorithm.
We give a classical algorithm for linear regression analogous to the quantum matrix inversion algorithm [Harrow, Hassidim, and Lloyd, Physical Review Letters'09] for low-rank matrices [Wossnig, Zhao, and Prakash, Physical Review Letters'18], when the input matrix A is stored in a data structure applicable for QRAM-based state preparation.Namely, suppose we are given an A∈Cm×n with minimum non-zero singular value σ which supports certain efficient ℓ2 -norm importance sampling queries, along with a b∈Cm . Then, for some x∈Cn satisfying ‖x–A+b‖≤ε‖A+b‖ , we can output a measurement of |x⟩ in the computational basis and output an entry of x with classical algorithms that run in O~(‖A‖F6‖A‖6σ12ε4) and O~(‖A‖F6‖A‖2σ8ε4) time, respectively. This improves on previous "quantum-inspired" algorithms in this line of research by at least a factor of ‖A‖16σ16ε2 [Chia, Gilyén, Li, Lin, Tang, and Wang, STOC'20]. As a consequence, we show that quantum computers can achieve at most a factor-of-12 speedup for linear regression in this QRAM data structure setting and related settings. Our work applies techniques from sketching algorithms and optimization to the quantum-inspired literature. Unlike earlier works, this is a promising avenue that could lead to feasible implementations of classical regression in a quantum-inspired settings, for comparison against future quantum computers.
We propose a quantum algorithm for support matrix machines (SMMs) that efficiently addresses an image classification problem by introducing a least-squares reformulation. This algorithm consists of two core subroutines: a quantum matrix inversion (Harrow-Hassidim-Lloyd, HHL) algorithm and a quantum singular value thresholding (QSVT) algorithm. The two algorithms can be implemented on a universal quantum computer with complexity O[log(npq)]O\left[log\left(npq\right)\right]O[log(npq)] and O[log(pq)]O\left[log\left(pq\right)\right]O[log(pq)], respectively, where nnn is the number of the training data and pqpqpq is the size of the feature space. By iterating the algorithms, we can find the parameters for the SMM classfication model. Our analysis shows that both HHL and QSVT algorithms achieve an exponential increase of speed over their classical counterparts.
We construct an efficient classical analogue of the quantum matrix inversion algorithm (HHL) for low-rank matrices. Inspired by recent work of Tang, assuming length-square sampling access to input data, we implement the pseudoinverse of a low-rank matrix and sample from the solution to the problem Ax=bAx=bAx=b using fast sampling techniques. We implement the pseudo-inverse by finding an approximate singular value decomposition of AAA via subsampling, then inverting the singular values. In principle, the approach can also be used to apply any desired "smooth" function to the singular values. Since many quantum algorithms can be expressed as a singular value transformation problem, our result suggests that more low-rank quantum algorithms can be effectively "dequantised" into classical length-square sampling algorithms.
With the significant advancement in quantum computation during the past couple of decades, the exploration of machine-learning subroutines using quantum strategies has become increasingly popular. Gaussian process regression is a widely used technique in supervised classical machine learning. Here we introduce an algorithm for Gaussian process regression using continuous-variable quantum systems that can be realized with technology based on photonic quantum computers under certain assumptions regarding distribution of data and availability of efficient quantum access. Our algorithm shows that by using a continuous-variable quantum computer a dramatic speedup in computing Gaussian process regression can be achieved, i.e., the possibility of exponentially reducing the time to compute. Furthermore, our results also include a continuous-variable quantum-assisted singular value decomposition method of nonsparse low rank matrices and forms an important subroutine in our Gaussian process regression algorithm.
Most quantum algorithms offering speedups over classical algorithms are based on the three techniques of phase estimation, amplitude estimation and Hamiltonian simulation. In spite of the linear algebraic nature of the postulates of quantum mechanics, until recent work by Lloyd and coauthors cite{LMR13, LMR13a, LMR13b} no quantum algorithms achieving speedups for linear algebra or machine learning had been proposed. A quantum machine learning algorithm must address three issues: encoding of classical data into a succinct quantum representation, processing the quantum representation and extraction of classically useful information from the processed quantum state. In this dissertation, we make progress on all three aspects of the quantum machine learning problem and obtain quantum algorithms for low rank approximation and regularized least squares. The oracle QRAMQRAMQRAM, the standard model studied in quantum query complexity, requires time O(sqrtn)O(sqrt{n})O(sqrtn) to encode vectors vinRnv in R^{n}vinRn into quantum states. We propose simple hardware augmentations to the oracle QRAMQRAMQRAM, that enable vectors vinRnv in R^{n}vinRn to be encoded in time O(logn)O(log n)O(logn), with pre-processing. The augmented QRAMQRAMQRAM incurs minimal hardware overheads, the pre-processing can be parallelized and is a flexible model that allows storage of multiple vectors and matrices. It provides a framework for designing quantum algorithms for linear algebra and machine learning. Using the augmented QRAMQRAMQRAM for vector state preparation, we present two different algorithms for singular value estimation where given singular vector ketvket{v}ketv for AinRmtimesnA in R^{mtimes n}AinRmtimesn, the singular value sigmaisigma_{i}sigmai​ is estimated within additive error epsilonnormAFepsilon norm{A}_{F}epsilonnormAF​. The first algorithm requires time wt1/epsilon3wt{1/epsilon^{3}}wt1/epsilon3 and uses the approach for simulating e−irhoe^{-i rho}e−irho in cite{LMR13}. However, the analysis cite{LMR13} does not establish the coherence of outputs, we provide a qualitatively different analysis that uses the quantum Zeno effect to establish coherence and reveals the probabilistic nature of the simulation technique. The second algorithm has a running time wt1/epsilonwt{1/epsilon}wt1/epsilon and uses Jordan's lemma from linear algebra and the augmented QRAMQRAMQRAM to implement reflections. We use quantum singular value estimation to obtain algorithms for low rank approximation by column selection, the algorithms are based on importance sampling from the leverage score distribution. We obtain quadratic speedups for a large class of linear algebra algorithms that rely on importance sampling from the leverage score distribution including approximate least squares and CXCXCX and CURCURCUR decompositions. Classical algorithms for these problems require time O(mnlogn+poly(1/epsilon))O(mn log n + poly(1/epsilon))O(mnlogn+poly(1/epsilon)), the quantum algorithms have running time O(sqrtmpoly(1/epsilon,k,Delta))O(sqrt{m}poly(1/epsilon, k, Delta))O(sqrtmpoly(1/epsilon,k,Delta)) where k,Deltak, Deltak,Delta are the rank and spectral gap. The running time of the quantum CXCXCX decomposition algorithm does not depend on mmm, it is polynomial in problem parameters. We also provide quantum algorithms for ell2ell_{2}ell2​ regularized regression problems, the quantum ridge regression algorithm requires time wt1/mu2deltawt{1/mu^{2} delta}wt1/mu2delta to output a quantum state that is deltadeltadelta close to the solution, where mumumu is the regularization parameter.
This dissertation presents a study of quantum algorithms for problems that can be posed as matrix function tasks. In Chapter 1 we demonstrate a simple unifying framework for implementing of smooth functions of matrices on a quantum computer. This framework captures a variety of problems that can be solved by evaluating properties of some function of a matrix, and we identify speedups over classical algorithms for some problem classes. The analysis combines ideas from the classical theory of function approximation with the quantum algorithmic primitive of implementing linear combinations of unitary operators. In Chapter 2 we continue this study by looking at the role of sparsity of input matrices in constructing efficient quantum algorithms. We show that classically pre-processing an input matrix by spectral sparsification can be profitable for quantum Hamiltonian simulation algorithms, without compromising the simulation error or complexity. Such preprocessing incurs a one time cost linear in the size of the matrix, but can be exploited to exponentially speed up subsequent subroutines such as inversion. In Chapter 3, we give an application of this theory of matrix functions to the problem of estimating the Renyi entropy of an unknown quantum state. We combine matrix function techniques with mixed state quantum computation in the one-clean qubit model, and are able to bound of the expected runtime of our algorithm in terms of the unknown target quantity. In addition to the theme of analysing the complexity of our algorithms, we also identify instances that are of practical relevance, leading us to some problems of machine learning. In Chapter 4 we investigate kernel based learning methods using random features. We work with the QRAM input model suitable for big data, and show how matrix functions and the quantum Fourier transform can be used to devise a quantum algorithm for sampling random features that are optimised for given input data and choice of kernel. We obtain a potential exponential speedup over the best known classical algorithm even without explicit assumptions of sparsity or low rank. Finally in Chapter 5 we consider the technique of beamsearch decoding used in natural language processing. We work in the query model, and show how quantum search with advice can be used to construct a quantum search decoder that can find the optimal parse (which may for instance be a best translation, or text-to-speech transcript) at least quadratically faster than the best known classical algorithms, and obtain super-quadratic speedups in the expected runtime.