{"id":679,"date":"2024-12-19T07:01:37","date_gmt":"2024-12-19T07:01:37","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2024\/12\/19\/2412-13928\/"},"modified":"2024-12-19T07:01:37","modified_gmt":"2024-12-19T07:01:37","slug":"2412-13928","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2024\/12\/19\/2412-13928\/","title":{"rendered":"Preconditioned Subspace Langevin Monte Carlo"},"content":{"rendered":"<p>    Preconditioned Subspace Langevin Monte Carlo<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2412.13928v1 Announce Type: new<br \/>\nAbstract: We develop a new efficient method for high-dimensional sampling called Subspace Langevin Monte Carlo. The primary application of these methods is to efficiently implement Preconditioned Langevin Monte Carlo. To demonstrate the usefulness of this new method, we extend ideas from subspace descent methods in Euclidean space to solving a specific optimization problem over Wasserstein space. Our theoretical analysis demonstrates the advantageous convergence regimes of the proposed method, which depend on relative conditioning assumptions common to mirror descent methods. We back up our theory with experimental evidence on sampling from an ill-conditioned Gaussian distribution.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Tyler Maunu, Jiayi Yao<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2412.13928\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Preconditioned Subspace Langevin Monte Carlo arXiv:2412.13928v1 Announce Type: new Abstract: We develop a new efficient method for high-dimensional sampling called Subspace Langevin Monte Carlo. The primary application of these methods is to efficiently implement Preconditioned Langevin Monte Carlo. To demonstrate the usefulness of this new method, we extend ideas from subspace descent methods in Euclidean [&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":[718,720,792],"class_list":["post-679","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-langevin","tag-monte","tag-subspace"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/679"}],"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=679"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/679\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=679"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=679"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=679"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}