---
res:
  bibo_abstract:
  - We study efficient distributed algorithms for the fundamental problem of principal
    component analysis and leading eigenvector computation on the sphere, when the
    data are randomly distributed among a set of computational nodes. We propose a
    new quantized variant of Riemannian gradient descent to solve this problem, and
    prove that the algorithm converges with high probability under a set of necessary
    spherical-convexity properties. We give bounds on the number of bits transmitted
    by the algorithm under common initialization schemes, and investigate the dependency
    on the problem dimension in each case.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Foivos
      foaf_name: Alimisis, Foivos
      foaf_surname: Alimisis
  - foaf_Person:
      foaf_givenName: Peter
      foaf_name: Davies, Peter
      foaf_surname: Davies
      foaf_workInfoHomepage: http://www.librecat.org/personId=11396234-BB50-11E9-B24C-90FCE5697425
    orcid: 0000-0002-5646-9524
  - foaf_Person:
      foaf_givenName: Bart
      foaf_name: Vandereycken, Bart
      foaf_surname: Vandereycken
  - foaf_Person:
      foaf_givenName: Dan-Adrian
      foaf_name: Alistarh, Dan-Adrian
      foaf_surname: Alistarh
      foaf_workInfoHomepage: http://www.librecat.org/personId=4A899BFC-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0003-3650-940X
  bibo_volume: 4
  dct_date: 2021^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/1049-5258
  - http://id.crossref.org/issn/9781713845393
  dct_language: eng
  dct_publisher: Neural Information Processing Systems Foundation@
  dct_title: Distributed principal component analysis with limited communication@
...