{"id":10701,"date":"2026-02-24T07:02:30","date_gmt":"2026-02-24T07:02:30","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2026\/02\/24\/2602-18718\/"},"modified":"2026-02-24T07:02:30","modified_gmt":"2026-02-24T07:02:30","slug":"2602-18718","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2026\/02\/24\/2602-18718\/","title":{"rendered":"Stochastic Gradient Variational Inference with Price&#8217;s Gradient Estimator from Bures-Wasserstein to Parameter Space"},"content":{"rendered":"\n<div>Stochastic Gradient Variational Inference with Price&#8217;s Gradient Estimator from Bures-Wasserstein to Parameter Space<\/div>\n<p> \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2602.18718v1 Announce Type: new<br \/>\nAbstract: For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform gradient descent in measure space (Bures-Wasserstein space) and parameter space, respectively. Previously, for the Gaussian variational family, convergence guarantees for WVI have shown superiority over existing results for black-box VI with the reparametrization gradient, suggesting the measure space approach might provide some unique benefits. In this work, however, we close this gap by obtaining identical state-of-the-art iteration complexity guarantees for both. In particular, we identify that WVI&#8217;s superiority stems from the specific gradient estimator it uses, which BBVI can also leverage with minor modifications. The estimator in question is usually associated with Price&#8217;s theorem and utilizes second-order information (Hessians) of the target log-density. We will refer to this as Price&#8217;s gradient. On the flip side, WVI can be made more widely applicable by using the reparametrization gradient, which requires only gradients of the log-density. We empirically demonstrate that the use of Price&#8217;s gradient is the major source of performance improvement.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Kyurae Kim, Qiang Fu, Yi-An Ma, Jacob R. Gardner, Trevor Campbell<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2602.18718\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Stochastic Gradient Variational Inference with Price&#8217;s Gradient Estimator from Bures-Wasserstein to Parameter Space arXiv:2602.18718v1 Announce Type: new Abstract: For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform gradient descent in measure space (Bures-Wasserstein space) [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,376,482,112],"tags":[379,3411,607],"class_list":["post-10701","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-math-oc","category-stat-co","category-stat-ml","tag-gradient","tag-price","tag-space"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10701"}],"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=10701"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10701\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=10701"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=10701"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=10701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}