{"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/semi-implicit-variational-inference","title":"Semi-Implicit Variational Inference","arxiv_id":"1805.11183","date":"2018-05-28","proceeding":"ICML 2018 7","authors":["Mingzhang Yin","Mingyuan Zhou"],"abstract":"Semi-implicit variational inference (SIVI) is introduced to expand the\ncommonly used analytic variational distribution family, by mixing the\nvariational parameter with a flexible distribution. This mixing distribution\ncan assume any density function, explicit or not, as long as independent random\nsamples can be generated via reparameterization. Not only does SIVI expand the\nvariational family to incorporate highly flexible variational distributions,\nincluding implicit ones that have no analytic density functions, but also\nsandwiches the evidence lower bound (ELBO) between a lower bound and an upper\nbound, and further derives an asymptotically exact surrogate ELBO that is\namenable to optimization via stochastic gradient ascent. With a substantially\nexpanded variational family and a novel optimization algorithm, SIVI is shown\nto closely match the accuracy of MCMC in inferring the posterior in a variety\nof Bayesian inference tasks.","url_abs":"http://arxiv.org/abs/1805.11183v1","url_pdf":"http://arxiv.org/pdf/1805.11183v1.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":"semi-implicit-variational-inference","repo_url":"https://github.com/mingzhang-yin/SIVI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11183","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}