{"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/enhanced-variational-inference-with-dyadic","title":"Enhanced Variational Inference with Dyadic Transformation","arxiv_id":"1901.10621","date":"2019-01-30","proceeding":null,"authors":["Sarin Chandy","Amin Rasekh"],"abstract":"Variational autoencoder is a powerful deep generative model with variational\ninference. The practice of modeling latent variables in the VAE's original\nformulation as normal distributions with a diagonal covariance matrix limits\nthe flexibility to match the true posterior distribution. We propose a new\ntransformation, dyadic transformation (DT), that can model a multivariate\nnormal distribution. DT is a single-stage transformation with low computational\nrequirements. We demonstrate empirically on MNIST dataset that DT enhances the\nposterior flexibility and attains competitive results compared to other VAE\nenhancements.","url_abs":"http://arxiv.org/abs/1901.10621v2","url_pdf":"http://arxiv.org/pdf/1901.10621v2.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":"enhanced-variational-inference-with-dyadic","repo_url":"https://github.com/sarin1991/DyadicFlow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}