{"id":7596,"date":"2025-10-15T07:03:08","date_gmt":"2025-10-15T07:03:08","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/10\/15\/2510-11895\/"},"modified":"2025-10-15T07:03:08","modified_gmt":"2025-10-15T07:03:08","slug":"2510-11895","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/10\/15\/2510-11895\/","title":{"rendered":"High-Probability Bounds For Heterogeneous Local Differential Privacy"},"content":{"rendered":"<p>    High-Probability Bounds For Heterogeneous Local Differential Privacy<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2510.11895v1 Announce Type: new<br \/>\nAbstract: We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper bounds in $ell_2$-norm that hold with probability at least $1-beta$. We complement these results with matching minimax lower bounds, establishing the optimality (up to constants) of our guarantees in the heterogeneous LDP regime. We further study distribution learning in $ell_infty$-distance, designing an algorithm with high-probability guarantees under heterogeneous privacy demands. Our techniques offer principled guidance for designing mechanisms in settings with user-specific privacy levels.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Maryam Aliakbarpour, Alireza Fallah, Swaha Roy, Ria Stevens<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2510.11895\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>High-Probability Bounds For Heterogeneous Local Differential Privacy arXiv:2510.11895v1 Announce Type: new Abstract: We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,412,413,113,112],"tags":[4003,654,921],"class_list":["post-7596","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-cr","category-cs-ds","category-cs-lg","category-stat-ml","tag-heterogeneous","tag-privacy","tag-probability"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7596"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=7596"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7596\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=7596"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=7596"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=7596"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}