{"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/vfunc-a-deep-generative-model-for-functions","title":"VFunc: a Deep Generative Model for Functions","arxiv_id":"1807.04106","date":"2018-07-11","proceeding":null,"authors":["Philip Bachman","Riashat Islam","Alessandro Sordoni","Zafarali Ahmed"],"abstract":"We introduce a deep generative model for functions. Our model provides a\njoint distribution p(f, z) over functions f and latent variables z which lets\nus efficiently sample from the marginal p(f) and maximize a variational lower\nbound on the entropy H(f). We can thus maximize objectives of the form\nE_{f~p(f)}[R(f)] + c*H(f), where R(f) denotes, e.g., a data log-likelihood term\nor an expected reward. Such objectives encompass Bayesian deep learning in\nfunction space, rather than parameter space, and Bayesian deep RL with\nrepresentations of uncertainty that offer benefits over bootstrapping and\nparameter noise. In this short paper we describe our model, situate it in the\ncontext of prior work, and present proof-of-concept experiments for regression\nand RL.","url_abs":"http://arxiv.org/abs/1807.04106v1","url_pdf":"http://arxiv.org/pdf/1807.04106v1.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":"vfunc-a-deep-generative-model-for-functions","repo_url":"https://github.com/zafarali/emdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.04106","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}