{"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/arbitrary-conditional-distributions-with","title":"Arbitrary Conditional Distributions with Energy","arxiv_id":"2102.04426","date":"2021-02-08","proceeding":"NeurIPS 2021 12","authors":["Ryan R. Strauss","Junier B. Oliva"],"abstract":"Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited utility in practical situations. A more general and useful problem is arbitrary conditional density estimation, which aims to model any possible conditional distribution over a set of covariates, reflecting the more realistic setting of inference based on prior knowledge. We propose a novel method, Arbitrary Conditioning with Energy (ACE), that can simultaneously estimate the distribution $p(\\mathbf{x}_u \\mid \\mathbf{x}_o)$ for all possible subsets of unobserved features $\\mathbf{x}_u$ and observed features $\\mathbf{x}_o$. ACE is designed to avoid unnecessary bias and complexity -- we specify densities with a highly expressive energy function and reduce the problem to only learning one-dimensional conditionals (from which more complex distributions can be recovered during inference). This results in an approach that is both simpler and higher-performing than prior methods. We show that ACE achieves state-of-the-art for arbitrary conditional likelihood estimation and data imputation on standard benchmarks.","url_abs":"https://arxiv.org/abs/2102.04426v3","url_pdf":"https://arxiv.org/pdf/2102.04426v3.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":"arbitrary-conditional-distributions-with","repo_url":"https://github.com/lupalab/ace","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"arbitrary-conditional-density-estimation","task_name":"Arbitrary Conditional Density Estimation"},{"task_slug":"imputation","task_name":"Imputation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.04426","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}