{"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/convex-learning-of-multiple-tasks-and-their","title":"Convex Learning of Multiple Tasks and their Structure","arxiv_id":"1504.03101","date":"2015-04-13","proceeding":null,"authors":["Carlo Ciliberto","Youssef Mroueh","Tomaso Poggio","Lorenzo Rosasco"],"abstract":"Reducing the amount of human supervision is a key problem in machine learning\nand a natural approach is that of exploiting the relations (structure) among\ndifferent tasks. This is the idea at the core of multi-task learning. In this\ncontext a fundamental question is how to incorporate the tasks structure in the\nlearning problem.We tackle this question by studying a general computational\nframework that allows to encode a-priori knowledge of the tasks structure in\nthe form of a convex penalty; in this setting a variety of previously proposed\nmethods can be recovered as special cases, including linear and non-linear\napproaches. Within this framework, we show that tasks and their structure can\nbe efficiently learned considering a convex optimization problem that can be\napproached by means of block coordinate methods such as alternating\nminimization and for which we prove convergence to the global minimum.","url_abs":"http://arxiv.org/abs/1504.03101v2","url_pdf":"http://arxiv.org/pdf/1504.03101v2.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":"convex-learning-of-multiple-tasks-and-their","repo_url":"https://github.com/cciliber/matMTL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1504.03101","atlas_url":"https://app.syntology.ai/?focus=1504.03101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}