Localized spectrum slicing

DOI10.1090/MCOM/3166MaRDI QIDQ2981780zbMATH OpenOpenAlexFDO

Authors Lin Lin

Publication date 10 May 2017

Published in Mathematics of Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1411.6152

zbMATH Keywords

eigenvectorlocalizationdecay propertiesspectrum slicinginterior eigenvalue problemsparse Hermitian matrixbasis setmatrix Gaussian functions

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Estimates of eigenvalues in context of PDEs (35P15) Numerical methods for eigenvalue problems for boundary value problems involving PDEs (65N25) Numerical computation of matrix exponential and similar matrix functions (65F60)

Abstract: Given a sparse Hermitian matrix $A$ and a real number $mu$, we construct a set of sparse vectors, each approximately spanned only by eigenvectors of $A$ corresponding to eigenvalues near $mu$. This set of vectors spans the column space of a localized spectrum slicing (LSS) operator, and is called an LSS basis set. The sparsity of the LSS basis set is related to the decay properties of matrix Gaussian functions. We present a divide-and-conquer strategy with controllable error to construct the LSS basis set. This is a purely algebraic process using only submatrices of $A$, and can therefore be applied to general sparse Hermitian matrices. The LSS basis set leads to sparse projected matrices with reduced sizes, which allows the projected problems to be solved efficiently with techniques using sparse linear algebra. As an example, we demonstrate that the LSS basis set can be used to solve interior eigenvalue problems for a discretized second order partial differential operator in one-dimensional and two-dimensional domains, as well as for a matrix of general sparsity pattern.

Recommendations

• Computing the eigenvalues of symmetric \(\mathcal{H}^2\)-matrices by slicing the spectrum
• Fast computation of spectral densities for generalized eigenvalue problems
• Strategies for spectrum slicing based on restarted Lanczos methods
• Localized bases of eigensubspaces and operator compression
• FEAST as a subspace iteration eigensolver accelerated by approximate spectral projection

Cites work

• scientific article; zbMATH DE number 3915823 (Why is no real title available?)
• scientific article; zbMATH DE number 961607 (Why is no real title available?)
• A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
• A column approximate minimum degree ordering algorithm
• A projection method for generalized eigenvalue problems using numerical integration.
• A spectrum slicing method for the Kohn-Sham problem
• Adaptive local basis set for Kohn-Sham density functional theory in a discontinuous Galerkin framework. I: Total energy calculation
• Bounds for the entries of matrix functions with applications to preconditioning
• Decay Rates for Inverses of Band Matrices
• Decay bounds and \(O(n)\) algorithms for approximating functions of sparse matrices
• Decay properties of spectral projectors with applications to electronic structure
• Existence of the exponentially localized Wannier functions
• Inverses of Band Matrices and Local Convergence of Spline Projections
• Nested Dissection of a Regular Finite Element Mesh
• New estimates for Ritz vectors
• New iterative methods for solution of the eigenproblem
• Remark on a Lemma by R. Wong and J. P. McClure
• SIPs
• The University of Florida sparse matrix collection
• The iterative calculation of a few of the lowest eigenvalues and corresponding eigenvectors of large real-symmetric matrices
• Toward the optimal preconditioned eigensolver: Locally optimal block preconditioned conjugate gradient method

Cited in

(7)

• Decay bounds for functions of Hermitian matrices with banded or Kronecker structure
• Localization in matrix computations: theory and applications
• Numerical methods for Kohn–Sham density functional theory
• Globally constructed adaptive local basis set for spectral projectors of second order differential operators
• Disentanglement via Entanglement: A Unified Method for Wannier Localization
• Localized bases of eigensubspaces and operator compression
• Mathematical methods in quantum chemistry. Abstracts from the workshop held March 18--24, 2018

Describes a project that uses

Uses Software

• lobpcg.m
• Sips
• JDQZ
• SparseMatrix
• FEAST
• JDQR
• COLAMD

This page was built for publication: Localized spectrum slicing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2981780)