{"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/learning-scalable-deep-kernels-with-recurrent","title":"Learning Scalable Deep Kernels with Recurrent Structure","arxiv_id":"1610.08936","date":"2016-10-27","proceeding":null,"authors":["Maruan Al-Shedivat","Andrew Gordon Wilson","Yunus Saatchi","Zhiting Hu","Eric P. Xing"],"abstract":"Many applications in speech, robotics, finance, and biology deal with\nsequential data, where ordering matters and recurrent structures are common.\nHowever, this structure cannot be easily captured by standard kernel functions.\nTo model such structure, we propose expressive closed-form kernel functions for\nGaussian processes. The resulting model, GP-LSTM, fully encapsulates the\ninductive biases of long short-term memory (LSTM) recurrent networks, while\nretaining the non-parametric probabilistic advantages of Gaussian processes. We\nlearn the properties of the proposed kernels by optimizing the Gaussian process\nmarginal likelihood using a new provably convergent semi-stochastic gradient\nprocedure and exploit the structure of these kernels for scalable training and\nprediction. This approach provides a practical representation for Bayesian\nLSTMs. We demonstrate state-of-the-art performance on several benchmarks, and\nthoroughly investigate a consequential autonomous driving application, where\nthe predictive uncertainties provided by GP-LSTM are uniquely valuable.","url_abs":"http://arxiv.org/abs/1610.08936v3","url_pdf":"http://arxiv.org/pdf/1610.08936v3.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":"learning-scalable-deep-kernels-with-recurrent","repo_url":"https://github.com/alshedivat/keras-gp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-scalable-deep-kernels-with-recurrent","repo_url":"https://github.com/alshedivat/kgp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"smart-grid-prediction","task_name":"Smart Grid Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.08936","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}