{"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/linear-additive-markov-processes","title":"Linear Additive Markov Processes","arxiv_id":"1704.01255","date":"2017-04-05","proceeding":null,"authors":["Ravi Kumar","Maithra Raghu","Tamas Sarlos","Andrew Tomkins"],"abstract":"We introduce LAMP: the Linear Additive Markov Process. Transitions in LAMP\nmay be influenced by states visited in the distant history of the process, but\nunlike higher-order Markov processes, LAMP retains an efficient\nparametrization. LAMP also allows the specific dependence on history to be\nlearned efficiently from data. We characterize some theoretical properties of\nLAMP, including its steady-state and mixing time. We then give an algorithm\nbased on alternating minimization to learn LAMP models from data. Finally, we\nperform a series of real-world experiments to show that LAMP is more powerful\nthan first-order Markov processes, and even holds its own against deep\nsequential models (LSTMs) with a negligible increase in parameter complexity.","url_abs":"http://arxiv.org/abs/1704.01255v1","url_pdf":"http://arxiv.org/pdf/1704.01255v1.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":"linear-additive-markov-processes","repo_url":"https://github.com/bridget-smart/modified_lamp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}