Fundamental limits of online and distributed algorithms for statistical learning and estimation. Shamir, O. In Advances in Neural Information Processing Systems 27, NeurIPS'14, pages 163–171, 2014. [Sha14] Considers estimation tasks under various information constraints, such as memory or communication. Establishes results for sequentially interactive protocols for those problems by proving a lower bound on the "hide-and-seek" problem, that is, the mean estimation problem for high-dimensional product Bernoulli distributions with 1-sparse mean vectors.
bibtex @inproceedings{Shamir14,
title={Fundamental limits of online and distributed algorithms for statistical learning and estimation},
author={Shamir, Ohad},
booktitle= {Advances in Neural Information Processing Systems 27, {NeurIPS'14}},
pages={163--171},
year={2014},
bibbase_note = {<div class="well well-small bibbase"><span class="bluecite">[Sha14]</span> Considers estimation tasks under various information constraints, such as memory or communication. Establishes results for sequentially interactive protocols for those problems by proving a lower bound on the "hide-and-seek" problem, that is, the mean estimation problem for high-dimensional product Bernoulli distributions with 1-sparse mean vectors.</div>}
}
Downloads: 0
{"_id":"m8DBpE3SRfdKRK32A","bibbaseid":"shamir-fundamentallimitsofonlineanddistributedalgorithmsforstatisticallearningandestimation-2014","authorIDs":[],"author_short":["Shamir, O."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Fundamental limits of online and distributed algorithms for statistical learning and estimation","author":[{"propositions":[],"lastnames":["Shamir"],"firstnames":["Ohad"],"suffixes":[]}],"booktitle":"Advances in Neural Information Processing Systems 27, NeurIPS'14","pages":"163–171","year":"2014","bibbase_note":"<div class=\"well well-small bibbase\"><span class=\"bluecite\">[Sha14]</span> Considers estimation tasks under various information constraints, such as memory or communication. Establishes results for sequentially interactive protocols for those problems by proving a lower bound on the \"hide-and-seek\" problem, that is, the mean estimation problem for high-dimensional product Bernoulli distributions with 1-sparse mean vectors.</div>","bibtex":"@inproceedings{Shamir14,\n title={Fundamental limits of online and distributed algorithms for statistical learning and estimation},\n author={Shamir, Ohad},\n booktitle= {Advances in Neural Information Processing Systems 27, {NeurIPS'14}},\n pages={163--171},\n year={2014},\n bibbase_note = {<div class=\"well well-small bibbase\"><span class=\"bluecite\">[Sha14]</span> Considers estimation tasks under various information constraints, such as memory or communication. Establishes results for sequentially interactive protocols for those problems by proving a lower bound on the \"hide-and-seek\" problem, that is, the mean estimation problem for high-dimensional product Bernoulli distributions with 1-sparse mean vectors.</div>}\n}\n\n","author_short":["Shamir, O."],"key":"Shamir14","id":"Shamir14","bibbaseid":"shamir-fundamentallimitsofonlineanddistributedalgorithmsforstatisticallearningandestimation-2014","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"http://www.cs.columbia.edu/~ccanonne/tutorial-focs2020/publications-annotated.bib","creationDate":"2020-11-08T21:08:20.200Z","downloads":0,"keywords":[],"search_terms":["fundamental","limits","online","distributed","algorithms","statistical","learning","estimation","shamir"],"title":"Fundamental limits of online and distributed algorithms for statistical learning and estimation","year":2014,"dataSources":["EYbwRcMzLdr2qsboR","SK4pKeSrqk4BzgaZs"]}