{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-mean-estimation-with-sub-gaussian-rates","title":"Fast Mean Estimation with Sub-Gaussian Rates","arxiv_id":"1902.01998","date":"2019-02-06","proceeding":null,"authors":["Yeshwanth Cherapanamjeri","Nicolas Flammarion","Peter L. Bartlett"],"abstract":"We propose an estimator for the mean of a random vector in $\\mathbb{R}^d$\nthat can be computed in time $O(n^4+n^2d)$ for $n$ i.i.d.~samples and that has\nerror bounds matching the sub-Gaussian case. The only assumptions we make about\nthe data distribution are that it has finite mean and covariance; in\nparticular, we make no assumptions about higher-order moments. Like the\npolynomial time estimator introduced by Hopkins, 2018, which is based on the\nsum-of-squares hierarchy, our estimator achieves optimal statistical efficiency\nin this challenging setting, but it has a significantly faster runtime and a\nsimpler analysis.","url_abs":"http://arxiv.org/abs/1902.01998v1","url_pdf":"http://arxiv.org/pdf/1902.01998v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-mean-estimation-with-sub-gaussian-rates","repo_url":"https://github.com/karimtito/Median_SDP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.01998","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}