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

Quantum Algorithms for Matrix Problems and Machine Learning

Sathyawageeswar Subramanian

Published Jul 24, 2020• 0 citations
Publisher

Abstract

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.

DOI
10.17863/cam.63762

Related papers

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 machine learning and optimization

Tongyang Li

The theories of optimization and machine learning answer foundational questions in computer science and lead to new algorithms for practical applications. While these topics have been extensively studied in the context of classical computing, their quantum counterparts are far from well-understood. In this thesis, we explore algorithms that bridge the gap between the fields of quantum computing and machine learning. First, we consider general optimization problems with only function evaluations. For two core problems, namely general convex optimization and volume estimation of convex bodies, we give quantum algorithms as well as quantum lower bounds that constitute the quantum speedups of both problems to be polynomial compared to their classical counterparts. We then consider machine learning and optimization problems with input data stored explicitly as matrices. We first look at semidefinite programs and provide quantum algorithms with polynomial speedup compared to the classical state-of-the-art. We then move to machine learning and give the optimal quantum algorithms for linear and kernel-based classifications. To complement with our quantum algorithms, we also introduce a framework for quantum-inspired classical algorithms, showing that for low-rank matrix arithmetics there can only be polynomial quantum speedup. Finally, we study statistical problems on quantum computers, with the focus on testing properties of probability distributions. We show that for testing various properties including L1-distance, L2-distance, Shannon and Renyi entropies, etc., there are polynomial quantum speedups compared to their classical counterparts. We also extend these results to testing properties of quantum states.

•Jan 1, 2020•2 citations

Quantum algorithms for linear algebra and machine learning. - eScholarship

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•0 citations

Efficient algorithms in quantum query complexity

Robin Kothari

In this thesis we provide new upper and lower bounds on the quantum query complexity of a diverse set of problems. Specifically, we study quantum algorithms for Hamiltonian simulation, matrix multiplication, oracle identification, and graph-property recognition. \n \nFor the Hamiltonian simulation problem, we provide a quantum algorithm with query complexity sublogarithmic in the inverse error, an exponential improvement over previous methods. Our algorithm is based on a new quantum algorithm for implementing unitary matrices that can be written as linear combinations of efficiently implementable unitary gates. This algorithm uses a new form of ``oblivious amplitude amplification'' that can be applied even though the reflection about the input state is unavailable. \n \nIn the oracle identification problem, we are given oracle access to an unknown N-bit string x promised to belong to a known set of size M, and our task is to identify x. We present the first quantum algorithm for the problem that is optimal in its dependence on N and M. Our algorithm is based on ideas from classical learning theory and a new composition theorem for solutions of the filtered gamma_2-norm semidefinite program. \n \nWe then study the quantum query complexity of matrix multiplication and related problems over rings, semirings, and the Boolean semiring in particular. Our main result is an output-sensitive algorithm for Boolean matrix multiplication that multiplies two n x n Boolean matrices with query complexity O(n sqrt{l}), where l is the sparsity of the output matrix. The algorithm is based on a reduction to the graph collision problem and a new algorithm for graph collision. \n \nFinally, we study the quantum query complexity of minor-closed graph properties and show that most minor-closed properties---those that cannot be characterized by a finite set of forbidden subgraphs---have quantum query complexity Theta(n^{3/2}) and those that do have such a characterization can be solved strictly faster, with o(n^{3/2}) queries. Our lower bound is based on a detailed analysis of the structure of minor-closed properties with respect to forbidden topological minors and forbidden subgraphs. Our algorithms are a novel application of the quantum walk search framework and give improved upper bounds for several subgraph-finding problems.

•Aug 13, 2014•26 citations

Quantum Algorithms and Complexity for Numerical Problems

Zhang, Chi

Quantum computing has attracted a lot of attention in different research fields, such as mathematics, physics and computer science. Quantum algorithms can solve certain problems significantly faster than classical algorithms. There are many numerical problems, especially those arising from quantum systems, which are notoriously difficult to solve using classical computers, since the computational time required often scales exponentially with the size of the problem. However, quantum computers have the potential to solve these problems efficiently, which is also one of the founding ideas of the field of quantum computing. In this thesis, we explore five computational problems, designing innovative quantum algorithms and studying their computational complexity. First, we design an adiabatic quantum algorithm based on the Berry phases for the counting problem. For the running time, it is not as good as the optimal algorithm in the quantum circuit model, but better than the classical random algorithm. Moreover, since the Berry phase is a purely geometric feature, the result should be robust to decoherence and resilient to certain kinds of noise. Since the counting problem is the foundation of many other numerical problems, such as high-dimensional integration and path integration, our adiabatic algorithms can be directly generalized to these kinds of problems. In addition, we study the quantum PAC learning model, offering an improved lower bound on the query complexity. The lower bound is very close to the best lower bound on query complexity known for the classical PAC learning model. We also study the algorithms and the cost of simulating a system evolving under a given Hamiltonian. We consider high order splitting methods that are particularly applicable in quantum simulation and obtain bounds on the number of exponentials required. Moreover, we derive the optimal order of convergence given the required error bound. We compare our complexity estimates to previously known ones and show the resulting speedup. Furthermore, we consider randomized algorithms for Hamiltonian simulation. The evolution is simulated by a product of exponentials in a random sequence and random evolution times. Hence the final state of the system is approximated by a mixed quantum state. We provide a scheme to bound the error of the final quantum state in a randomized algorithm, and obtain randomized algorithms which have the same efficiency as certain deterministic algorithms but which are simpler to implement. We also apply Hamiltonian simulation in estimating the ground state energy of a multiparticle system, which is also known as the multivariate Sturm-Liouville eigenvalue problem. Since the cost of this problem grows exponentially with the number of particles using deterministic classical algorithms, it suffers from the curse of dimensionality. Quantum computers can vanquish the curse, and we exhibit a quantum algorithm whose total cost are linear in the number of particles.

•Jan 1, 2011•0 citations

Accelerating linear algebra and machine learning with quantum computers

AG Rattew

In this thesis, I develop the theory required to use quantum computers to accelerate linear algebra and machine learning, in a manner akin to how GPUs are used today. I begin by analysing quantum random access memory (QRAM), the mechanism by which quantum algorithms can access classical (non-quantum) data. When used for linear algebra applications, I show that QRAM has substantial challenges making it harder to construct than an error-corrected quantum computer. Should QRAM prove to be unrealistic, I ask what types of classical data can be efficiently loaded into quantum computers, and prove that discretized continuous functions are one such option. Next, I introduce a framework for manipulating vectors with quantum computers. The primary result of this framework is a technique allowing for the non-linear transformations of vectors to be enacted efficiently for a broad class of functions, despite the underlying unitary (and thus linear) nature of quantum algorithms. In the final chapter, utilizing the preceding results and further developing the vector encoding framework, I demonstrate that quantum computers can accelerate inference for multilayer neural networks under a range of scenarios of QRAM feasibility. This chapter also notes a plausible path towards constructing a practically useful QRAM.

•Jan 1, 2025•0 citations
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.
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.
The theories of optimization and machine learning answer foundational questions in computer science and lead to new algorithms for practical applications. While these topics have been extensively studied in the context of classical computing, their quantum counterparts are far from well-understood. In this thesis, we explore algorithms that bridge the gap between the fields of quantum computing and machine learning. First, we consider general optimization problems with only function evaluations. For two core problems, namely general convex optimization and volume estimation of convex bodies, we give quantum algorithms as well as quantum lower bounds that constitute the quantum speedups of both problems to be polynomial compared to their classical counterparts. We then consider machine learning and optimization problems with input data stored explicitly as matrices. We first look at semidefinite programs and provide quantum algorithms with polynomial speedup compared to the classical state-of-the-art. We then move to machine learning and give the optimal quantum algorithms for linear and kernel-based classifications. To complement with our quantum algorithms, we also introduce a framework for quantum-inspired classical algorithms, showing that for low-rank matrix arithmetics there can only be polynomial quantum speedup. Finally, we study statistical problems on quantum computers, with the focus on testing properties of probability distributions. We show that for testing various properties including L1-distance, L2-distance, Shannon and Renyi entropies, etc., there are polynomial quantum speedups compared to their classical counterparts. We also extend these results to testing properties of quantum states.
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.
In this thesis we provide new upper and lower bounds on the quantum query complexity of a diverse set of problems. Specifically, we study quantum algorithms for Hamiltonian simulation, matrix multiplication, oracle identification, and graph-property recognition. \n \nFor the Hamiltonian simulation problem, we provide a quantum algorithm with query complexity sublogarithmic in the inverse error, an exponential improvement over previous methods. Our algorithm is based on a new quantum algorithm for implementing unitary matrices that can be written as linear combinations of efficiently implementable unitary gates. This algorithm uses a new form of ``oblivious amplitude amplification'' that can be applied even though the reflection about the input state is unavailable. \n \nIn the oracle identification problem, we are given oracle access to an unknown N-bit string x promised to belong to a known set of size M, and our task is to identify x. We present the first quantum algorithm for the problem that is optimal in its dependence on N and M. Our algorithm is based on ideas from classical learning theory and a new composition theorem for solutions of the filtered gamma_2-norm semidefinite program. \n \nWe then study the quantum query complexity of matrix multiplication and related problems over rings, semirings, and the Boolean semiring in particular. Our main result is an output-sensitive algorithm for Boolean matrix multiplication that multiplies two n x n Boolean matrices with query complexity O(n sqrt{l}), where l is the sparsity of the output matrix. The algorithm is based on a reduction to the graph collision problem and a new algorithm for graph collision. \n \nFinally, we study the quantum query complexity of minor-closed graph properties and show that most minor-closed properties---those that cannot be characterized by a finite set of forbidden subgraphs---have quantum query complexity Theta(n^{3/2}) and those that do have such a characterization can be solved strictly faster, with o(n^{3/2}) queries. Our lower bound is based on a detailed analysis of the structure of minor-closed properties with respect to forbidden topological minors and forbidden subgraphs. Our algorithms are a novel application of the quantum walk search framework and give improved upper bounds for several subgraph-finding problems.
Quantum computing has attracted a lot of attention in different research fields, such as mathematics, physics and computer science. Quantum algorithms can solve certain problems significantly faster than classical algorithms. There are many numerical problems, especially those arising from quantum systems, which are notoriously difficult to solve using classical computers, since the computational time required often scales exponentially with the size of the problem. However, quantum computers have the potential to solve these problems efficiently, which is also one of the founding ideas of the field of quantum computing. In this thesis, we explore five computational problems, designing innovative quantum algorithms and studying their computational complexity. First, we design an adiabatic quantum algorithm based on the Berry phases for the counting problem. For the running time, it is not as good as the optimal algorithm in the quantum circuit model, but better than the classical random algorithm. Moreover, since the Berry phase is a purely geometric feature, the result should be robust to decoherence and resilient to certain kinds of noise. Since the counting problem is the foundation of many other numerical problems, such as high-dimensional integration and path integration, our adiabatic algorithms can be directly generalized to these kinds of problems. In addition, we study the quantum PAC learning model, offering an improved lower bound on the query complexity. The lower bound is very close to the best lower bound on query complexity known for the classical PAC learning model. We also study the algorithms and the cost of simulating a system evolving under a given Hamiltonian. We consider high order splitting methods that are particularly applicable in quantum simulation and obtain bounds on the number of exponentials required. Moreover, we derive the optimal order of convergence given the required error bound. We compare our complexity estimates to previously known ones and show the resulting speedup. Furthermore, we consider randomized algorithms for Hamiltonian simulation. The evolution is simulated by a product of exponentials in a random sequence and random evolution times. Hence the final state of the system is approximated by a mixed quantum state. We provide a scheme to bound the error of the final quantum state in a randomized algorithm, and obtain randomized algorithms which have the same efficiency as certain deterministic algorithms but which are simpler to implement. We also apply Hamiltonian simulation in estimating the ground state energy of a multiparticle system, which is also known as the multivariate Sturm-Liouville eigenvalue problem. Since the cost of this problem grows exponentially with the number of particles using deterministic classical algorithms, it suffers from the curse of dimensionality. Quantum computers can vanquish the curse, and we exhibit a quantum algorithm whose total cost are linear in the number of particles.
In this thesis, I develop the theory required to use quantum computers to accelerate linear algebra and machine learning, in a manner akin to how GPUs are used today. I begin by analysing quantum random access memory (QRAM), the mechanism by which quantum algorithms can access classical (non-quantum) data. When used for linear algebra applications, I show that QRAM has substantial challenges making it harder to construct than an error-corrected quantum computer. Should QRAM prove to be unrealistic, I ask what types of classical data can be efficiently loaded into quantum computers, and prove that discretized continuous functions are one such option. Next, I introduce a framework for manipulating vectors with quantum computers. The primary result of this framework is a technique allowing for the non-linear transformations of vectors to be enacted efficiently for a broad class of functions, despite the underlying unitary (and thus linear) nature of quantum algorithms. In the final chapter, utilizing the preceding results and further developing the vector encoding framework, I demonstrate that quantum computers can accelerate inference for multilayer neural networks under a range of scenarios of QRAM feasibility. This chapter also notes a plausible path towards constructing a practically useful QRAM.