{"external_id":{"arxiv":["2110.14391"]},"date_published":"2021-12-01T00:00:00Z","abstract":[{"lang":"eng","text":"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."}],"ec_funded":1,"acknowledgement":"We would like to thank the anonymous reviewers for helpful comments and suggestions. We also thank Aurelien Lucchi and Antonio Orvieto for fruitful discussions at an early stage of this work. FA is partially supported by the SNSF under research project No. 192363 and conducted part of this work while at IST Austria under the European Union’s Horizon 2020 research and innovation programme (grant agreement No. 805223 ScaleML). PD partly conducted this work while at IST Austria and was supported by the European Union’s Horizon 2020 programme under the Marie Skłodowska-Curie grant agreement No. 754411.","author":[{"full_name":"Alimisis, Foivos","first_name":"Foivos","last_name":"Alimisis"},{"orcid":"0000-0002-5646-9524","id":"11396234-BB50-11E9-B24C-90FCE5697425","last_name":"Davies","first_name":"Peter","full_name":"Davies, Peter"},{"last_name":"Vandereycken","first_name":"Bart","full_name":"Vandereycken, Bart"},{"last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X"}],"language":[{"iso":"eng"}],"_id":"11452","publication_status":"published","department":[{"_id":"DaAl"}],"conference":{"start_date":"2021-12-06","location":"Virtual, Online","name":"NeurIPS: Neural Information Processing Systems","end_date":"2021-12-14"},"article_processing_charge":"No","main_file_link":[{"open_access":"1","url":"https://proceedings.neurips.cc/paper/2021/file/1680e9fa7b4dd5d62ece800239bb53bd-Paper.pdf"}],"date_created":"2022-06-19T22:01:58Z","date_updated":"2022-06-20T08:31:52Z","publication_identifier":{"issn":["1049-5258"],"isbn":["9781713845393"]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","page":"2823-2834","volume":4,"oa":1,"project":[{"call_identifier":"H2020","grant_number":"805223","_id":"268A44D6-B435-11E9-9278-68D0E5697425","name":"Elastic Coordination for Scalable Machine Learning"},{"_id":"260C2330-B435-11E9-9278-68D0E5697425","grant_number":"754411","call_identifier":"H2020","name":"ISTplus - Postdoctoral Fellowships"}],"publication":"Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems","month":"12","quality_controlled":"1","scopus_import":"1","oa_version":"Published Version","title":"Distributed principal component analysis with limited communication","intvolume":"         4","status":"public","day":"01","type":"conference","year":"2021","citation":{"ista":"Alimisis F, Davies P, Vandereycken B, Alistarh D-A. 2021. Distributed principal component analysis with limited communication. Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 4, 2823–2834.","mla":"Alimisis, Foivos, et al. “Distributed Principal Component Analysis with Limited Communication.” <i>Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems</i>, vol. 4, Neural Information Processing Systems Foundation, 2021, pp. 2823–34.","ama":"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.","ieee":"F. Alimisis, P. Davies, B. Vandereycken, and D.-A. Alistarh, “Distributed principal component analysis with limited communication,” in <i>Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems</i>, Virtual, Online, 2021, vol. 4, pp. 2823–2834.","chicago":"Alimisis, Foivos, Peter Davies, Bart Vandereycken, and Dan-Adrian Alistarh. “Distributed Principal Component Analysis with Limited Communication.” In <i>Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems</i>, 4:2823–34. Neural Information Processing Systems Foundation, 2021.","short":"F. Alimisis, P. Davies, B. Vandereycken, D.-A. Alistarh, in:, Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2021, pp. 2823–2834.","apa":"Alimisis, F., Davies, P., Vandereycken, B., &#38; Alistarh, D.-A. (2021). 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, pp. 2823–2834). Virtual, Online: Neural Information Processing Systems Foundation."},"publisher":"Neural Information Processing Systems Foundation"}