Robust Dequantization of the Quantum Singular value Transformation and Quantum Machine Learning Algorithms

by   François Le Gall, et al.

Several quantum algorithms for linear algebra problems, and in particular quantum machine learning problems, have been "dequantized" in the past few years. These dequantization results typically hold when classical algorithms can access the data via length-squared sampling. In this work we investigate how robust these dequantization results are. We introduce the notion of approximate length-squared sampling, where classical algorithms are only able to sample from a distribution close to the ideal distribution in total variation distance. While quantum algorithms are natively robust against small perturbations, current techniques in dequantization are not. Our main technical contribution is showing how many techniques from randomized linear algebra can be adapted to work under this weaker assumption as well. We then use these techniques to show that the recent low-rank dequantization framework by Chia, Gilyén, Li, Lin, Tang and Wang (JACM 2022) and the dequantization framework for sparse matrices by Gharibian and Le Gall (STOC 2022), which are both based on the Quantum Singular Value Transformation, can be generalized to the case of approximate length-squared sampling access to the input. We also apply these results to obtain a robust dequantization of many quantum machine learning algorithms, including quantum algorithms for recommendation systems, supervised clustering and low-rank matrix inversion.


page 1

page 2

page 3

page 4


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

We construct an efficient classical analogue of the quantum matrix inver...

Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning

We present an algorithmic framework generalizing quantum-inspired polylo...

An Improved Classical Singular Value Transformation for Quantum Machine Learning

Quantum machine learning (QML) has shown great potential to produce larg...

Multiplicative Rank-1 Approximation using Length-Squared Sampling

We show that the span of Ω(1/ε^4) rows of any matrix A ⊂R^n × d sampled ...

Quantum-inspired classical sublinear-time algorithm for solving low-rank semidefinite programming via sampling approaches

Semidefinite programming (SDP) is a central topic in mathematical optimi...

Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra

We create classical (non-quantum) dynamic data structures supporting que...

Distributional property testing in a quantum world

A fundamental problem in statistics and learning theory is to test prope...

Please sign up or login with your details

Forgot password? Click here to reset