{"id":6383,"date":"2025-08-27T07:02:33","date_gmt":"2025-08-27T07:02:33","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/08\/27\/2508-18768\/"},"modified":"2025-08-27T07:02:33","modified_gmt":"2025-08-27T07:02:33","slug":"2508-18768","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/08\/27\/2508-18768\/","title":{"rendered":"Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits"},"content":{"rendered":"

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2508.18768v1 Announce Type: new
\nAbstract: We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $widetilde{mathcal{O}}(sqrt{T})$ regret in the adversarial regime and $widetilde{mathcal{O}}(ln T)$ regret in the corrupted stochastic regime. Our approach builds on the Follow-the-Regularized-Leader (FTRL) framework equipped with a Shannon entropy regularizer, yielding a flexible method that admits efficient implementations. Beyond regret bounds, we tackle the practical bottleneck in FTRL (or, equivalently, Online Stochastic Mirror Descent) arising from the high-dimensional projection step encountered in each round of interaction. By leveraging the Karush-Kuhn-Tucker conditions, we transform the $K$-dimensional convex projection problem into a single-variable root-finding problem, dramatically accelerating each round. Empirical evaluations demonstrate that this combined strategy not only attains the attractive regret bounds of best-of-both-worlds algorithms but also delivers substantial per-round speed-ups, making it well-suited for large-scale, real-time applications.<\/div>\n

\t

\n
<\/BR>
\n Mengmeng Li, Philipp Schneider, Jelisaveta Aleksi’c, Daniel Kuhn
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits arXiv:2508.18768v1 Announce Type: new Abstract: We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $widetilde{mathcal{O}}(sqrt{T})$ regret in the adversarial regime and $widetilde{mathcal{O}}(ln T)$ regret in the corrupted stochastic regime. Our approach builds on the Follow-the-Regularized-Leader (FTRL) framework equipped with a Shannon entropy regularizer, yielding […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[1015,3612,3613],"class_list":["post-6383","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-best","tag-both","tag-worlds"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6383"}],"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=6383"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6383\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=6383"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=6383"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=6383"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}