Contour Integral-based Quantum Algorithm for Estimating Matrix Eigenvalue Density

TL;DR

This paper introduces a quantum algorithm that estimates the eigenvalue density of a matrix within a specified interval using contour integrals, the HHL solver, and quantum Fourier transform, relevant for scientific computing tasks.

Contribution

The paper presents a novel quantum algorithm combining contour integrals, the HHL solver, and QFT to efficiently estimate eigenvalue densities, reducing system size via symmetry exploitation.

Findings

Demonstrates how to approximate eigenvalue counts using quantum methods.

Shows the integration of HHL solver and QFT for eigenvalue density estimation.

Provides a framework for applying quantum algorithms to scientific computing problems.

Abstract

The eigenvalue density of a matrix plays an important role in various types of scientific computing such as electronic-structure calculations. In this paper, we propose a quantum algorithm for computing the eigenvalue density in a given interval. Our quantum algorithm is based on a method that approximates the eigenvalue counts by applying the numerical contour integral and the stochastic trace estimator applied to a matrix involving resolvent matrices. As components of our algorithm, the HHL solver is applied to an augmented linear system of the resolvent matrices, and the quantum Fourier transform (QFT) is adopted to represent the operation of the numerical contour integral. To reduce the size of the augmented system, we exploit a certain symmetry of the numerical integration. We also introduce a permutation formed by CNOT gates to make the augmented system solution consistent with the QFT input. The eigenvalue count in a given interval is derived as the probability of observing a bit pattern in a fraction of the qubits of the output state.