Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Sampling-based Sublinear Low-rank Matrix Arithmetic Framework for Dequantizing Quantum Machine Learning

Journal Article · · Journal of the Association for Computing Machinery
DOI:https://doi.org/10.1145/3549524· OSTI ID:2424704
 [1];  [2];  [3];  [1];  [4];  [5]
  1. Department of Computer Science, University of Texas at Austin, USA
  2. Alfréd Rényi Institute of Mathematics Hungary and Institute for Quantum Information and Matter, California Institute of Technology, USA
  3. Center on Frontiers of Computing Studies, School of Computer Science, Peking University China and Center for Theoretical Physics, Massachusetts Institute of Technology, USA
  4. University of Washington, WA, USA
  5. Department of Computer Science and Engineering, Pennsylvania State University, USA and Department of Computer Science, University of Texas at Austin, USA

We present an algorithmic framework for quantum-inspired classical algorithms on close-to-low-rank matrices, generalizing the series of results started by Tang’s breakthrough quantum-inspired algorithm for recommendation systems [STOC’19]. Motivated by quantum linear algebra algorithms and the quantum singular value transformation (SVT) framework of Gilyén et al. [STOC’19], we develop classical algorithms for SVT that run in time independent of input dimension, under suitable quantum-inspired sampling assumptions. Our results give compelling evidence that in the corresponding QRAM data structure input model, quantum SVT does not yield exponential quantum speedups. Since the quantum SVT framework generalizes essentially all known techniques for quantum linear algebra, our results, combined with sampling lemmas from previous work, suffice to generalize all prior results about dequantizing quantum machine learning algorithms. In particular, our classical SVT framework recovers and often improves the dequantization results on recommendation systems, principal component analysis, supervised clustering, support vector machines, low-rank regression, and semidefinite program solving. We also give additional dequantization results on low-rank Hamiltonian simulation and discriminant analysis. Our improvements come from identifying the key feature of the quantum-inspired input model that is at the core of all prior quantum-inspired results: ℓ2-norm sampling can approximate matrix products in time independent of their dimension. We reduce all our main results to this fact, making our exposition concise, self-contained, and intuitive.

Research Organization:
US Department of Energy (USDOE), Washington, DC (United States). Office of Science, Advanced Scientific Computing Research (ASCR)
Sponsoring Organization:
USDOE
OSTI ID:
2424704
Journal Information:
Journal of the Association for Computing Machinery, Journal Name: Journal of the Association for Computing Machinery Journal Issue: 5 Vol. 69; ISSN 0004-5411
Publisher:
Association for Computing Machinery (ACM)
Country of Publication:
United States
Language:
English

References (66)

Quantum Computing in the NISQ era and beyond journal August 2018
Quantum Recommendation Systems text January 2017
A non-review of Quantum Machine Learning: trends and explorations journal March 2020
Quantum gradient descent and Newton’s method for constrained polynomial optimization journal July 2019
Quantum gradient descent for linear systems and least squares journal February 2020
Eigenfaces vs. Fisherfaces: recognition using class specific linear projection
  • Belhumeur, P. N.; Hespanha, J. P.; Kriegman, D. J.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, Issue 7 https://doi.org/10.1109/34.598228
journal July 1997
Quantum Algorithm for Linear Systems of Equations journal October 2009
Estimates of operator moduli of continuity journal November 2011
Quantum algorithmic measurement journal February 2022
Hamiltonian Simulation with Nearly Optimal Dependence on all Parameters conference October 2015
Quantum-inspired algorithm for general minimum conical hull problems journal August 2020
Quantum Principal Component Analysis Only Achieves an Exponential Speedup Because of Its State Preparation Assumptions journal August 2021
Input Sparsity Time Low-rank Approximation via Ridge Leverage Score Sampling conference January 2017
Polynomials and Polynomial Inequalities book January 1995
An Empirical Evaluation of Sketching for Numerical Linear Algebra conference July 2018
Information-Theoretic Bounds on Quantum Advantage in Machine Learning journal May 2021
Quantum Support Vector Machine for Big Data Classification journal September 2014
A quantum-inspired classical algorithm for recommendation systems conference January 2019
Quantum-Inspired Support Vector Machine journal December 2022
Quantum Random Access Memory journal April 2008
Quantum discriminant analysis for dimensionality reduction and classification journal July 2016
Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication journal January 2006
Read the fine print journal April 2015
Universal Quantum Simulators journal August 1996
An Operator Calculus Having Applications in Quantum Electrodynamics journal October 1951
Sampling from large matrices: An approach through geometric functional analysis journal July 2007
Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer journal October 1997
Operator Hölder–Zygmund functions journal June 2010
Quantum principal component analysis journal July 2014
Simulating physics with computers journal June 1982
A Note on Saturation in Microwave Spectroscopy journal May 1948
Quantum-Inspired Algorithms for Solving Low-Rank Linear Equation Systems with Logarithmic Dependence on the Dimension text January 2020
Quantum Linear System Algorithm for Dense Matrices journal January 2018
The Power of Block-Encoded Matrix Powers: Improved Regression Techniques via Faster Hamiltonian Simulation text January 2019
A linear algorithm for generating random numbers with a given distribution journal January 1991
Relative-Error $CUR$ Matrix Decompositions journal January 2008
Computational Advertising: Techniques for Targeting Relevant Ads journal January 2014
Competitive recommendation systems conference May 2002
A randomized algorithm for a tensor-based generalization of the singular value decomposition journal January 2007
Perturbations of functions of diagonalizable matrices journal January 2010
Lower Bounds on the Size of Semidefinite Programming Relaxations conference June 2015
Optimal Hamiltonian Simulation by Quantum Signal Processing journal January 2017
Grand Unification of Quantum Algorithms journal December 2021
Quantum-inspired algorithms in practice journal August 2020
Quantum-Inspired Classical Algorithms for Singular Value Transformation conferencepaper January 2020
The complexity of the matrix eigenproblem conference January 1999
Quantum machine learning: a classical perspective
  • Ciliberto, Carlo; Herbster, Mark; Ialongo, Alessandro Davide
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 474, Issue 2209 https://doi.org/10.1098/rspa.2017.0551
journal January 2018
Tensor-CUR Decompositions for Tensor-Based Data journal January 2008
Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics conference January 2019
Fast monte-carlo algorithms for finding low-rank approximations journal November 2004
Low-Rank Approximation and Regression in Input Sparsity Time journal January 2017
Randomized algorithms in numerical linear algebra journal May 2017
A Combinatorial, Primal-Dual Approach to Semidefinite Programs journal May 2016
Quantum algorithms for topological and geometric analysis of data journal January 2016
Quantum SDP-Solvers: Better upper and lower bounds journal February 2020
Quantum-Inspired Sublinear Algorithm for Solving Low-Rank Semidefinite Programming conferencepaper January 2020
Quantum Speed-Ups for Solving Semidefinite Programs conference October 2017
Improvements in Quantum SDP-Solving with Applications text January 2019
A Quantum-inspired Classical Algorithm for Separable Non-negative Matrix Factorization conference August 2019
Quantum SDP Solvers: Large Speed-Ups, Optimality, and Applications to Quantum Learning text January 2019
Approximating Hamiltonian dynamics with the Nyström method journal February 2020
Adiabatic quantum state generation and statistical zero knowledge conference January 2003
Matrix Analysis book November 1996
Approximate quantum circuit synthesis using block encodings journal November 2020
Quantum-assisted Gaussian process regression journal May 2019
Randomized Algorithms for Matrices and Data journal January 2010

Similar Records

Geometric dequantization
Journal Article · 2005 · Annals of Physics (New York) · OSTI ID:20690148

Dynamical aspects in the quantizer–dequantizer formalism
Journal Article · 2017 · Annals of Physics · OSTI ID:22701550

Grand Unification of Quantum Algorithms
Journal Article · 2021 · PRX Quantum · OSTI ID:1982849

Related Subjects