Distributed principal component analysis with limited communication Alimisis, Foivos Davies, Peter ; https://orcid.org/0000-0002-5646-9524 Vandereycken, Bart Alistarh, Dan-Adrian ; https://orcid.org/0000-0003-3650-940X 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. Neural Information Processing Systems Foundation 2021 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://research-explorer.ista.ac.at/record/11452 Alimisis F, Davies P, Vandereycken B, Alistarh D-A. Distributed principal component analysis with limited communication. In: <i>Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems</i>. Vol 4. Neural Information Processing Systems Foundation; 2021:2823-2834. eng info:eu-repo/semantics/altIdentifier/issn/1049-5258 info:eu-repo/semantics/altIdentifier/isbn/9781713845393 info:eu-repo/semantics/altIdentifier/arxiv/2110.14391 info:eu-repo/semantics/openAccess