{"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/improving-variational-auto-encoders-using","title":"Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow","arxiv_id":"1706.02326","date":"2017-06-07","proceeding":null,"authors":["Jakub M. Tomczak","Max Welling"],"abstract":"In this paper, we propose a new volume-preserving flow and show that it\nperforms similarly to the linear general normalizing flow. The idea is to\nenrich a linear Inverse Autoregressive Flow by introducing multiple\nlower-triangular matrices with ones on the diagonal and combining them using a\nconvex combination. In the experimental studies on MNIST and Histopathology\ndata we show that the proposed approach outperforms other volume-preserving\nflows and is competitive with current state-of-the-art linear normalizing flow.","url_abs":"http://arxiv.org/abs/1706.02326v2","url_pdf":"http://arxiv.org/pdf/1706.02326v2.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":"improving-variational-auto-encoders-using","repo_url":"https://github.com/jmtomczak/vae_vpflows","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02326","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}