An Improved Classical Singular Value Transformation for Quantum Machine Learning

• URL: http://arxiv.org/abs/2303.01492v4
• Date: Sun, 28 Jul 2024 21:30:43 GMT
• Title: An Improved Classical Singular Value Transformation for Quantum Machine Learning
• Authors: Ainesh Bakshi, Ewin Tang,
• Abstract summary: We study quantum speedups in quantum machine learning (QML) by analyzing the quantum singular value transformation (QSVT) framework. Our key insight is to combine the Clenshaw recurrence, an iterative method for computing matrix stability, with sketching techniques to simulate QSVT classically.
• Score: 2.3326951882644553
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study quantum speedups in quantum machine learning (QML) by analyzing the quantum singular value transformation (QSVT) framework. QSVT, introduced by [GSLW, STOC'19, arXiv:1806.01838], unifies all major types of quantum speedup; in particular, a wide variety of QML proposals are applications of QSVT on low-rank classical data. We challenge these proposals by providing a classical algorithm that matches the performance of QSVT in this regime up to a small polynomial overhead. We show that, given a matrix $A \in \mathbb{C}^{m\times n}$, a vector $b \in \mathbb{C}^{n}$, a bounded degree-$d$ polynomial $p$, and linear-time pre-processing, we can output a description of a vector $v$ such that $\|v - p(A) b\| \leq \varepsilon\|b\|$ in $\widetilde{\mathcal{O}}(d^{11} \|A\|_{\mathrm{F}}^4 / (\varepsilon^2 \|A\|^4 ))$ time. This improves upon the best known classical algorithm [CGLLTW, STOC'20, arXiv:1910.06151], which requires $\widetilde{\mathcal{O}}(d^{22} \|A\|_{\mathrm{F}}^6 /(\varepsilon^6 \|A\|^6 ) )$ time, and narrows the gap with QSVT, which, after linear-time pre-processing to load input into a quantum-accessible memory, can estimate the magnitude of an entry $p(A)b$ to $\varepsilon\|b\|$ error in $\widetilde{\mathcal{O}}(d\|A\|_{\mathrm{F}}/(\varepsilon \|A\|))$ time. Our key insight is to combine the Clenshaw recurrence, an iterative method for computing matrix polynomials, with sketching techniques to simulate QSVT classically. We introduce several new classical techniques in this work, including (a) a non-oblivious matrix sketch for approximately preserving bi-linear forms, (b) a new stability analysis for the Clenshaw recurrence, and (c) a new technique to bound arithmetic progressions of the coefficients appearing in the Chebyshev series expansion of bounded functions, each of which may be of independent interest.

Related papers

• A shortcut to an optimal quantum linear system solver [55.2480439325792]
  We give a conceptually simple quantum linear system solvers (QLSS) that does not use complex or difficult-to-analyze techniques. If the solution norm $lVertboldsymbolxrVert$ is known exactly, our QLSS requires only a single application of kernel. Alternatively, by reintroducing a concept from the adiabatic path-following technique, we show that $O(kappa)$ complexity can be achieved for norm estimation.
  arXiv  Detail & Related papers  (2024-06-17T20:54:11Z)
• Calculating response functions of coupled oscillators using quantum phase estimation [40.31060267062305]
  We study the problem of estimating frequency response functions of systems of coupled, classical harmonic oscillators using a quantum computer. Our proposed quantum algorithm operates in the standard $s-sparse, oracle-based query access model. We show that a simple adaptation of our algorithm solves the random glued-trees problem in time.
  arXiv  Detail & Related papers  (2024-05-14T15:28:37Z)
• Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters [10.602399256297032]
  We develop a quantum algorithm that runs in $widetildeO(epsilon-1sqrtnd1.5) + mathrmpoly(d/epsilon)$ time. It provides a quadratic quantum speedup in $n over the classical lower bound without any dependence on data-dependent parameters.
  arXiv  Detail & Related papers  (2023-11-24T19:41:28Z)
• Fast and Practical Quantum-Inspired Classical Algorithms for Solving Linear Systems [11.929584800629673]
  We propose fast and practical quantum-inspired classical algorithms for solving linear systems. Our main contribution is the application of the heavy ball momentum method to quantum-inspired classical algorithms for solving linear systems.
  arXiv  Detail & Related papers  (2023-07-13T08:46:19Z)
• Quantum and classical low-degree learning via a dimension-free Remez inequality [52.12931955662553]
  We show a new way to relate functions on the hypergrid to their harmonic extensions over the polytorus. We show the supremum of a function $f$ over products of the cyclic group $exp(2pi i k/K)_k=1K$. We extend to new spaces a recent line of work citeEI22, CHP, VZ22 that gave similarly efficient methods for learning low-degrees on hypercubes and observables on qubits.
  arXiv  Detail & Related papers  (2023-01-04T04:15:40Z)
• Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits [8.682187438614296]
  A quantum algorithm finds an $x*incal K$ such that $F(x*)-min_xincal K F(x)leqepsilon$ using $tildeO(n3)$ quantum evaluation queries to $F$. As an application, we give a quantum function algorithm for zeroth-order convex bandits with $tildeO(n5log2 T)$ regret, an exponential speedup in $T$ compared to the classical $
  arXiv  Detail & Related papers  (2022-09-26T03:19:40Z)
• Quantum Resources Required to Block-Encode a Matrix of Classical Data [56.508135743727934]
  We provide circuit-level implementations and resource estimates for several methods of block-encoding a dense $Ntimes N$ matrix of classical data to precision $epsilon$. We examine resource tradeoffs between the different approaches and explore implementations of two separate models of quantum random access memory (QRAM) Our results go beyond simple query complexity and provide a clear picture into the resource costs when large amounts of classical data are assumed to be accessible to quantum algorithms.
  arXiv  Detail & Related papers  (2022-06-07T18:00:01Z)
• A lower bound on the space overhead of fault-tolerant quantum computation [51.723084600243716]
  The threshold theorem is a fundamental result in the theory of fault-tolerant quantum computation. We prove an exponential upper bound on the maximal length of fault-tolerant quantum computation with amplitude noise.
  arXiv  Detail & Related papers  (2022-01-31T22:19:49Z)
• Quantum algorithms for spectral sums [50.045011844765185]
  We propose new quantum algorithms for estimating spectral sums of positive semi-definite (PSD) matrices. We show how the algorithms and techniques used in this work can be applied to three problems in spectral graph theory.
  arXiv  Detail & Related papers  (2020-11-12T16:29:45Z)
• Finite-Time Analysis for Double Q-learning [50.50058000948908]
  We provide the first non-asymptotic, finite-time analysis for double Q-learning. We show that both synchronous and asynchronous double Q-learning are guaranteed to converge to an $epsilon$-accurate neighborhood of the global optimum.
  arXiv  Detail & Related papers  (2020-09-29T18:48:21Z)
• An improved quantum-inspired algorithm for linear regression [15.090593955414137]
  We give a classical algorithm for linear regression analogous to the quantum matrix inversion algorithm. We show that quantum computers can achieve at most a factor-of-12 speedup for linear regression in this QRAM data structure setting.
  arXiv  Detail & Related papers  (2020-09-15T17:58:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.