{"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/auto-encoding-sequential-monte-carlo","title":"Auto-Encoding Sequential Monte Carlo","arxiv_id":"1705.10306","date":"2017-05-29","proceeding":"ICLR 2018 1","authors":["Tuan Anh Le","Maximilian Igl","Tom Rainforth","Tom Jin","Frank Wood"],"abstract":"We build on auto-encoding sequential Monte Carlo (AESMC): a method for model\nand proposal learning based on maximizing the lower bound to the log marginal\nlikelihood in a broad family of structured probabilistic models. Our approach\nrelies on the efficiency of sequential Monte Carlo (SMC) for performing\ninference in structured probabilistic models and the flexibility of deep neural\nnetworks to model complex conditional probability distributions. We develop\nadditional theoretical insights and introduce a new training procedure which\nimproves both model and proposal learning. We demonstrate that our approach\nprovides a fast, easy-to-implement and scalable means for simultaneous model\nlearning and proposal adaptation in deep generative models.","url_abs":"http://arxiv.org/abs/1705.10306v2","url_pdf":"http://arxiv.org/pdf/1705.10306v2.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":"auto-encoding-sequential-monte-carlo","repo_url":"https://github.com/amoretti86/PSVO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10306","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}