{"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/far-ho-a-bilevel-programming-package-for","title":"Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning","arxiv_id":"1806.04941","date":"2018-06-13","proceeding":null,"authors":["Luca Franceschi","Riccardo Grazzi","Massimiliano Pontil","Saverio Salzo","Paolo Frasconi"],"abstract":"In (Franceschi et al., 2018) we proposed a unified mathematical framework,\ngrounded on bilevel programming, that encompasses gradient-based hyperparameter\noptimization and meta-learning. We formulated an approximate version of the\nproblem where the inner objective is solved iteratively, and gave sufficient\nconditions ensuring convergence to the exact problem. In this work we show how\nto optimize learning rates, automatically weight the loss of single examples\nand learn hyper-representations with Far-HO, a software package based on the\npopular deep learning framework TensorFlow that allows to seamlessly tackle\nboth HO and ML problems.","url_abs":"http://arxiv.org/abs/1806.04941v1","url_pdf":"http://arxiv.org/pdf/1806.04941v1.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":"far-ho-a-bilevel-programming-package-for","repo_url":"https://github.com/lucfra/FAR-HO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"far-ho-a-bilevel-programming-package-for","repo_url":"https://github.com/prolearner/hyper-representation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}