logo
Università della Svizzera italiana
  • Italiano
  • English
  • usi.ch
  • Info Desk
  • Campus map
search.usi
Search for contacts, projects,
courses and publications
Italiano
People
    Education
    • Education
    • Courses
    Research
    • Projects
    • Publications
    • Competences maps
    Organisation
    • Faculties
    • Other organizational units

    Distributed Memory Sparse Inverse Covariance Matrix Estimation on High-Performance Computing Architectures

    Additional information

    Authors
    Eftekhari A., Bollhoefer M., Schenk O.
    Type
    Article in conference proceedings
    Year
    2018
    Language
    English
    Abstract
    We consider the problem of estimating sparse inverse covariance matrices for high-dimensional datasets using the L1-regularized Gaussian maximum likelihood method. This task is particularly challenging as the required computational resources increase superlinearly with the dimensionality of the dataset. We introduce a performant and scalable algorithm which builds on the current advancements of second-order, maximum likelihood methods. The routine leverages the intrinsic parallelism in the linear algebra operations and exploits the underlying sparsity of the problem. The computational bottlenecks are identified and the respective subroutines are parallelized using an MPI-OpenMP approach. Numerical examples conducted on a 5,320 node Cray XC50 system at the Swiss National Supercomputing Center show that, in comparison to the state-of-the-art algorithms, the proposed routine provides significant strong-scaling speedup with ideal scalability up to 128 nodes. The developed framework is used to approximate the sparse inverse covariance matrix of both synthetic and real-world datasets with up to 10 million dimensions.
    Conference proceedings
    Proceedings of the ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis
    Month
    November
    Publisher
    ACM
    Meeting name
    SC18
    Meeting place
    Dallas, Texas
    Meeting date
    November 11 – 16, 2018
    Keywords
    inverse covariance matrix, sparse matrices, approximate matrix inverse, high-performance computing

    Faculties

    Faculty of Informatics

    Organizational units

    Institute of Computational Science (ICS)

    Università della
    Svizzera italiana

    Via Buffi 13
    6900 Lugano, Switzerland
    tel +41 58 666 40 00
    fax +41 58 666 46 47
    e-mail info@usi.ch
    Other contacts
    Feedback on the website

    Maps and directions

    • Lugano Campus
    • Mendrisio Campus
    • Bellinzona Campus

    Stay in touch

    • Facebook
    • Twitter
    • Instagram
    • Youtube
    • LinkedIn
    • Newsletter
    • Annual Report
    • Subscribe
    © Università della Svizzera italiana
    Disclaimer Credits
    swissuniversities.ch
    logo
    • Faculties
    • Institutes
    • Bodies
    • Libraries and archives
    • Areas
    • Services
    • Job offers