{"id":10503,"date":"2026-02-16T07:02:29","date_gmt":"2026-02-16T07:02:29","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2026\/02\/16\/2602-12680\/"},"modified":"2026-02-16T07:02:29","modified_gmt":"2026-02-16T07:02:29","slug":"2602-12680","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2026\/02\/16\/2602-12680\/","title":{"rendered":"A Regularization-Sharpness Tradeoff for Linear Interpolators"},"content":{"rendered":"

A Regularization-Sharpness Tradeoff for Linear Interpolators
\n \t

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

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

arXiv:2602.12680v1 Announce Type: new
\nAbstract: The rule of thumb regarding the relationship between the bias-variance tradeoff and model size plays a key role in classical machine learning, but is now well-known to break down in the overparameterized setting as per the double descent curve. In particular, minimum-norm interpolating estimators can perform well, suggesting the need for new tradeoff in these settings. Accordingly, we propose a regularization-sharpness tradeoff for overparameterized linear regression with an $ell^p$ penalty. Inspired by the interpolating information criterion, our framework decomposes the selection penalty into a regularization term (quantifying the alignment of the regularizer and the interpolator) and a geometric sharpness term on the interpolating manifold (quantifying the effect of local perturbations), yielding a tradeoff analogous to bias-variance. Building on prior analyses that established this information criterion for ridge regularizers, this work first provides a general expression of the interpolating information criterion for $ell^p$ regularizers where $p ge 2$. Subsequently, we extend this to the LASSO interpolator with $ell^1$ regularizer, which induces stronger sparsity. Empirical results on real-world datasets with random Fourier features and polynomials validate our theory, demonstrating how the tradeoff terms can distinguish performant linear interpolators from weaker ones.<\/div>\n

\t

\n
<\/BR>
\n Qingyi Hu, Liam Hodgkinson
\n \t

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

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

A Regularization-Sharpness Tradeoff for Linear Interpolators arXiv:2602.12680v1 Announce Type: new Abstract: The rule of thumb regarding the relationship between the bias-variance tradeoff and model size plays a key role in classical machine learning, but is now well-known to break down in the overparameterized setting as per the double descent curve. In particular, minimum-norm interpolating estimators […]<\/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":[765,2236,4782],"class_list":["post-10503","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-regularization","tag-sharpness","tag-tradeoff"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10503"}],"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=10503"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10503\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=10503"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=10503"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=10503"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}