{"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/deep-nonparametric-estimation-of-discrete","title":"Deep Nonparametric Estimation of Discrete Conditional Distributions via Smoothed Dyadic Partitioning","arxiv_id":"1702.07398","date":"2017-02-23","proceeding":null,"authors":["Wesley Tansey","Karl Pichotta","James G. Scott"],"abstract":"We present an approach to deep estimation of discrete conditional probability\ndistributions. Such models have several applications, including generative\nmodeling of audio, image, and video data. Our approach combines two main\ntechniques: dyadic partitioning and graph-based smoothing of the discrete\nspace. By recursively decomposing each dimension into a series of binary splits\nand smoothing over the resulting distribution using graph-based trend\nfiltering, we impose a strict structure to the model and achieve much higher\nsample efficiency. We demonstrate the advantages of our model through a series\nof benchmarks on both synthetic and real-world datasets, in some cases reducing\nthe error by nearly half in comparison to other popular methods in the\nliterature. All of our models are implemented in Tensorflow and publicly\navailable at https://github.com/tansey/sdp .","url_abs":"http://arxiv.org/abs/1702.07398v2","url_pdf":"http://arxiv.org/pdf/1702.07398v2.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":"deep-nonparametric-estimation-of-discrete","repo_url":"https://github.com/tansey/sdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}