{"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/conditional-density-estimation-with-neural","title":"Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks","arxiv_id":"1903.00954","date":"2019-03-03","proceeding":null,"authors":["Jonas Rothfuss","Fabio Ferreira","Simon Walther","Maxim Ulrich"],"abstract":"Given a set of empirical observations, conditional density estimation aims to\ncapture the statistical relationship between a conditional variable\n$\\mathbf{x}$ and a dependent variable $\\mathbf{y}$ by modeling their\nconditional probability $p(\\mathbf{y}|\\mathbf{x})$. The paper develops best\npractices for conditional density estimation for finance applications with\nneural networks, grounded on mathematical insights and empirical evaluations.\nIn particular, we introduce a noise regularization and data normalization\nscheme, alleviating problems with over-fitting, initialization and\nhyper-parameter sensitivity of such estimators. We compare our proposed\nmethodology with popular semi- and non-parametric density estimators, underpin\nits effectiveness in various benchmarks on simulated and Euro Stoxx 50 data and\nshow its superior performance. Our methodology allows to obtain high-quality\nestimators for statistical expectations of higher moments, quantiles and\nnon-linear return transformations, with very little assumptions about the\nreturn dynamic.","url_abs":"http://arxiv.org/abs/1903.00954v2","url_pdf":"http://arxiv.org/pdf/1903.00954v2.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":"conditional-density-estimation-with-neural","repo_url":"https://github.com/freelunchtheorem/Conditional_Density_Estimation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.00954","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}