{"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/infinite-horizon-gaussian-processes","title":"Infinite-Horizon Gaussian Processes","arxiv_id":"1811.06588","date":"2018-11-15","proceeding":"NeurIPS 2018 12","authors":["Arno Solin","James Hensman","Richard E. Turner"],"abstract":"Gaussian processes provide a flexible framework for forecasting, removing\nnoise, and interpreting long temporal datasets. State space modelling (Kalman\nfiltering) enables these non-parametric models to be deployed on long datasets\nby reducing the complexity to linear in the number of data points. The\ncomplexity is still cubic in the state dimension $m$ which is an impediment to\npractical application. In certain special cases (Gaussian likelihood, regular\nspacing) the GP posterior will reach a steady posterior state when the data are\nvery long. We leverage this and formulate an inference scheme for GPs with\ngeneral likelihoods, where inference is based on single-sweep EP (assumed\ndensity filtering). The infinite-horizon model tackles the cubic cost in the\nstate dimensionality and reduces the cost in the state dimension $m$ to\n$\\mathcal{O}(m^2)$ per data point. The model is extended to online-learning of\nhyperparameters. We show examples for large finite-length modelling problems,\nand present how the method runs in real-time on a smartphone on a continuous\ndata stream updated at 100~Hz.","url_abs":"http://arxiv.org/abs/1811.06588v1","url_pdf":"http://arxiv.org/pdf/1811.06588v1.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":"infinite-horizon-gaussian-processes","repo_url":"https://github.com/AaltoML/IHGP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.06588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}