{"id":10790,"date":"2026-02-27T07:02:26","date_gmt":"2026-02-27T07:02:26","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2026\/02\/27\/2602-22884\/"},"modified":"2026-02-27T07:02:26","modified_gmt":"2026-02-27T07:02:26","slug":"2602-22884","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2026\/02\/27\/2602-22884\/","title":{"rendered":"Unsupervised Continual Learning for Amortized Bayesian Inference"},"content":{"rendered":"

Unsupervised Continual Learning for Amortized Bayesian Inference
\n \t

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

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

arXiv:2602.22884v1 Announce Type: new
\nAbstract: Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC) training on unlabeled empirical data can enhance network robustness, current approaches are limited to static, single-task settings and fail to handle sequentially arriving data or distribution shifts. We propose a continual learning framework for ABI that decouples simulation-based pre-training from unsupervised sequential SC fine-tuning on real-world data. To address the challenge of catastrophic forgetting, we introduce two adaptation strategies: (1) SC with episodic replay, utilizing a memory buffer of past observations, and (2) SC with elastic weight consolidation, which regularizes updates to preserve task-critical parameters. Across three diverse case studies, our methods significantly mitigate forgetting and yield posterior estimates that outperform standard simulation-based training, achieving estimates closer to MCMC reference, providing a viable path for trustworthy ABI across a range of different tasks.<\/div>\n

\t

\n
<\/BR>
\n Aayush Mishra, v{S}imon Kucharsk’y, Paul-Christian B"urkner
\n \t

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

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

Unsupervised Continual Learning for Amortized Bayesian Inference arXiv:2602.22884v1 Announce Type: new Abstract: Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC) training on unlabeled empirical data can enhance network robustness, current approaches are limited to static, […]<\/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":[84,4846,2448],"class_list":["post-10790","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-data","tag-sc","tag-unsupervised"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10790"}],"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=10790"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/10790\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=10790"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=10790"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=10790"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}