{"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/bottleneck-conditional-density-estimation","title":"Bottleneck Conditional Density Estimation","arxiv_id":"1611.08568","date":"2016-11-25","proceeding":"ICML 2017 8","authors":["Rui Shu","Hung H. Bui","Mohammad Ghavamzadeh"],"abstract":"We introduce a new framework for training deep generative models for\nhigh-dimensional conditional density estimation. The Bottleneck Conditional\nDensity Estimator (BCDE) is a variant of the conditional variational\nautoencoder (CVAE) that employs layer(s) of stochastic variables as the\nbottleneck between the input $x$ and target $y$, where both are\nhigh-dimensional. Crucially, we propose a new hybrid training method that\nblends the conditional generative model with a joint generative model. Hybrid\nblending is the key to effective training of the BCDE, which avoids overfitting\nand provides a novel mechanism for leveraging unlabeled data. We show that our\nhybrid training procedure enables models to achieve competitive results in the\nMNIST quadrant prediction task in the fully-supervised setting, and sets new\nbenchmarks in the semi-supervised regime for MNIST, SVHN, and CelebA.","url_abs":"http://arxiv.org/abs/1611.08568v3","url_pdf":"http://arxiv.org/pdf/1611.08568v3.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":"bottleneck-conditional-density-estimation","repo_url":"https://github.com/ruishu/bcde","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08568","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}