{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-kalman-filters","title":"Deep Kalman Filters","arxiv_id":"1511.05121","date":"2015-11-16","proceeding":null,"authors":["Rahul G. Krishnan","Uri Shalit","David Sontag"],"abstract":"Kalman Filters are one of the most influential models of time-varying\nphenomena. They admit an intuitive probabilistic interpretation, have a simple\nfunctional form, and enjoy widespread adoption in a variety of disciplines.\nMotivated by recent variational methods for learning deep generative models, we\nintroduce a unified algorithm to efficiently learn a broad spectrum of Kalman\nfilters. Of particular interest is the use of temporal generative models for\ncounterfactual inference. We investigate the efficacy of such models for\ncounterfactual inference, and to that end we introduce the \"Healing MNIST\"\ndataset where long-term structure, noise and actions are applied to sequences\nof digits. We show the efficacy of our method for modeling this dataset. We\nfurther show how our model can be used for counterfactual inference for\npatients, based on electronic health record data of 8,000 patients over 4.5\nyears.","url_abs":"http://arxiv.org/abs/1511.05121v2","url_pdf":"http://arxiv.org/pdf/1511.05121v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-kalman-filters","repo_url":"https://github.com/clinicalml/structuredinference","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-kalman-filters","repo_url":"https://github.com/GalaxyFox/DS-GA-3001-Deep_Kalman_Filter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-kalman-filters","repo_url":"https://github.com/clinicalml/dmm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"counterfactual-inference","task_name":"Counterfactual Inference"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1511.05121","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}