{"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/myopic-bayesian-design-of-experiments-via","title":"Myopic Bayesian Design of Experiments via Posterior Sampling and Probabilistic Programming","arxiv_id":"1805.09964","date":"2018-05-25","proceeding":null,"authors":["Kirthevasan Kandasamy","Willie Neiswanger","Reed Zhang","Akshay Krishnamurthy","Jeff Schneider","Barnabas Poczos"],"abstract":"We design a new myopic strategy for a wide class of sequential design of\nexperiment (DOE) problems, where the goal is to collect data in order to to\nfulfil a certain problem specific goal. Our approach, Myopic Posterior Sampling\n(MPS), is inspired by the classical posterior (Thompson) sampling algorithm for\nmulti-armed bandits and leverages the flexibility of probabilistic programming\nand approximate Bayesian inference to address a broad set of problems.\nEmpirically, this general-purpose strategy is competitive with more specialised\nmethods in a wide array of DOE tasks, and more importantly, enables addressing\ncomplex DOE goals where no existing method seems applicable. On the theoretical\nside, we leverage ideas from adaptive submodularity and reinforcement learning\nto derive conditions under which MPS achieves sublinear regret against natural\nbenchmark policies.","url_abs":"http://arxiv.org/abs/1805.09964v1","url_pdf":"http://arxiv.org/pdf/1805.09964v1.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":"myopic-bayesian-design-of-experiments-via","repo_url":"https://github.com/kirthevasank/mps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"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}