{"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/embedding-reparameterization-procedure-for","title":"Embedding-reparameterization procedure for manifold-valued latent variables in generative models","arxiv_id":"1812.02769","date":"2018-12-06","proceeding":null,"authors":["Eugene Golikov","Maksim Kretov"],"abstract":"Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian\ndistribution. Recent works demonstrated that choice of prior distribution\naffects learning capacity of VAE models. We propose a general technique\n(embedding-reparameterization procedure, or ER) for introducing arbitrary\nmanifold-valued variables in VAE model. We compare our technique with a\nconventional VAE on a toy benchmark problem. This is work in progress.","url_abs":"http://arxiv.org/abs/1812.02769v1","url_pdf":"http://arxiv.org/pdf/1812.02769v1.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":"embedding-reparameterization-procedure-for","repo_url":"https://github.com/varenick/manifold_latent_vae","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}