{"id":9453,"date":"2026-01-01T07:02:55","date_gmt":"2026-01-01T07:02:55","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2026\/01\/01\/2512-23818\/"},"modified":"2026-01-01T07:02:55","modified_gmt":"2026-01-01T07:02:55","slug":"2512-23818","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2026\/01\/01\/2512-23818\/","title":{"rendered":"Energy-Tweedie: Score meets Score, Energy meets Energy"},"content":{"rendered":"<p>    Energy-Tweedie: Score meets Score, Energy meets Energy<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2512.23818v1 Announce Type: new<br \/>\nAbstract: Denoising and score estimation have long been known to be linked via the classical Tweedie&#8217;s formula. In this work, we first extend the latter to a wider range of distributions often called &#8220;energy models&#8221; and denoted elliptical distributions in this work. Next, we examine an alternative view: we consider the denoising posterior $P(X|Y)$ as the optimizer of the energy score (a scoring rule) and derive a fundamental identity that connects the (path-) derivative of a (possibly) non-Euclidean energy score to the score of the noisy marginal. This identity can be seen as an analog of Tweedie&#8217;s identity for the energy score, and allows for several interesting applications; for example, score estimation, noise distribution parameter estimation, as well as using energy score models in the context of &#8220;traditional&#8221; diffusion model samplers with a wider array of noising distributions.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Andrej Leban<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2512.23818\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Energy-Tweedie: Score meets Score, Energy meets Energy arXiv:2512.23818v1 Announce Type: new Abstract: Denoising and score estimation have long been known to be linked via the classical Tweedie&#8217;s formula. In this work, we first extend the latter to a wider range of distributions often called &#8220;energy models&#8221; and denoted elliptical distributions in this work. Next, we [&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":[372,856,4530],"class_list":["post-9453","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-energy","tag-score","tag-tweedie"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9453"}],"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=9453"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9453\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=9453"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=9453"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=9453"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}