{"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/autoregressive-quantile-networks-for","title":"Autoregressive Quantile Networks for Generative Modeling","arxiv_id":"1806.05575","date":"2018-06-14","proceeding":"ICML 2018 7","authors":["Georg Ostrovski","Will Dabney","Rémi Munos"],"abstract":"We introduce autoregressive implicit quantile networks (AIQN), a\nfundamentally different approach to generative modeling than those commonly\nused, that implicitly captures the distribution using quantile regression. AIQN\nis able to achieve superior perceptual quality and improvements in evaluation\nmetrics, without incurring a loss of sample diversity. The method can be\napplied to many existing models and architectures. In this work we extend the\nPixelCNN model with AIQN and demonstrate results on CIFAR-10 and ImageNet using\nInception score, FID, non-cherry-picked samples, and inpainting results. We\nconsistently observe that AIQN yields a highly stable algorithm that improves\nperceptual quality while maintaining a highly diverse distribution.","url_abs":"http://arxiv.org/abs/1806.05575v1","url_pdf":"http://arxiv.org/pdf/1806.05575v1.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":"autoregressive-quantile-networks-for","repo_url":"https://github.com/SSS135/aiqn-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"quantile-regression","task_name":"quantile regression"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1806.05575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}