{"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/variational-generative-stochastic-networks","title":"Variational Generative Stochastic Networks with Collaborative Shaping","arxiv_id":"1708.00805","date":"2017-08-02","proceeding":null,"authors":["Philip Bachman","Doina Precup"],"abstract":"We develop an approach to training generative models based on unrolling a\nvariational auto-encoder into a Markov chain, and shaping the chain's\ntrajectories using a technique inspired by recent work in Approximate Bayesian\ncomputation. We show that the global minimizer of the resulting objective is\nachieved when the generative model reproduces the target distribution. To allow\nfiner control over the behavior of the models, we add a regularization term\ninspired by techniques used for regularizing certain types of policy search in\nreinforcement learning. We present empirical results on the MNIST and TFD\ndatasets which show that our approach offers state-of-the-art performance, both\nquantitatively and from a qualitative point of view.","url_abs":"http://arxiv.org/abs/1708.00805v1","url_pdf":"http://arxiv.org/pdf/1708.00805v1.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":"variational-generative-stochastic-networks","repo_url":"https://github.com/Philip-Bachman/ICML-2015","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}