{"id":2219,"date":"2025-03-05T07:04:46","date_gmt":"2025-03-05T07:04:46","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/03\/05\/2503-02110\/"},"modified":"2025-03-05T07:04:46","modified_gmt":"2025-03-05T07:04:46","slug":"2503-02110","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/03\/05\/2503-02110\/","title":{"rendered":"Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification"},"content":{"rendered":"<p>    Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2503.02110v1 Announce Type: new<br \/>\nAbstract: We provide a complete characterization of the entire regularization curve of a modified two-part-code Minimum Description Length (MDL) learning rule for binary classification, based on an arbitrary prior or description language. citet{GL} previously established the lack of asymptotic consistency, from an agnostic PAC (frequentist worst case) perspective, of the MDL rule with a penalty parameter of $lambda=1$, suggesting that it underegularizes. Driven by interest in understanding how benign or catastrophic under-regularization and overfitting might be, we obtain a precise quantitative description of the worst case limiting error as a function of the regularization parameter $lambda$ and noise level (or approximation error), significantly tightening the analysis of citeauthor{GL} for $lambda=1$ and extending it to all other choices of $lambda$.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Xiaohan Zhu, Nathan Srebro<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2503.02110\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification arXiv:2503.02110v1 Announce Type: new Abstract: We provide a complete characterization of the entire regularization curve of a modified two-part-code Minimum Description Length (MDL) learning rule for binary classification, based on an arbitrary prior or description language. citet{GL} previously established the lack of asymptotic [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[1935,1934,765],"class_list":["post-2219","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-lambda","tag-mdl","tag-regularization"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/2219"}],"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=2219"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/2219\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=2219"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=2219"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=2219"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}