{"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/efficient-differentiable-programming-in-a","title":"Efficient Differentiable Programming in a Functional Array-Processing Language","arxiv_id":"1806.02136","date":"2018-06-06","proceeding":null,"authors":["Amir Shaikhha","Andrew Fitzgibbon","Dimitrios Vytiniotis","Simon Peyton Jones","Christoph Koch"],"abstract":"We present a system for the automatic differentiation of a higher-order\nfunctional array-processing language. The core functional language underlying\nthis system simultaneously supports both source-to-source automatic\ndifferentiation and global optimizations such as loop transformations. Thanks\nto this feature, we demonstrate how for some real-world machine learning and\ncomputer vision benchmarks, the system outperforms the state-of-the-art\nautomatic differentiation tools.","url_abs":"http://arxiv.org/abs/1806.02136v1","url_pdf":"http://arxiv.org/pdf/1806.02136v1.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":"efficient-differentiable-programming-in-a","repo_url":"https://github.com/Ojasvi-Jalal/Forward-mode-AD-in-a-functional-language","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02136","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}