{"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/probabilistic-recurrent-state-space-models","title":"Probabilistic Recurrent State-Space Models","arxiv_id":"1801.10395","date":"2018-01-31","proceeding":"ICML 2018 7","authors":["Andreas Doerr","Christian Daniel","Martin Schiegg","Duy Nguyen-Tuong","Stefan Schaal","Marc Toussaint","Sebastian Trimpe"],"abstract":"State-space models (SSMs) are a highly expressive model class for learning\npatterns in time series data and for system identification. Deterministic\nversions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex\ntime series data. Fully probabilistic SSMs, however, are often found hard to\ntrain, even for smaller problems. To overcome this limitation, we propose a\nnovel model formulation and a scalable training algorithm based on doubly\nstochastic variational inference and Gaussian processes. In contrast to\nexisting work, the proposed variational approximation allows one to fully\ncapture the latent state temporal correlations. These correlations are the key\nto robust training. The effectiveness of the proposed PR-SSM is evaluated on a\nset of real-world benchmark datasets in comparison to state-of-the-art\nprobabilistic model learning methods. Scalability and robustness are\ndemonstrated on a high dimensional problem.","url_abs":"http://arxiv.org/abs/1801.10395v2","url_pdf":"http://arxiv.org/pdf/1801.10395v2.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":"probabilistic-recurrent-state-space-models","repo_url":"https://github.com/andreasdoerr/PR-SSM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"probabilistic-recurrent-state-space-models","repo_url":"https://github.com/boschresearch/PR-SSM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"probabilistic-recurrent-state-space-models","repo_url":"https://github.com/zhidilin/gpssmproj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"probabilistic-recurrent-state-space-models","repo_url":"https://github.com/zhidilin/odgpssm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.10395","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}