{"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/quadratic-decomposable-submodular-function","title":"Quadratic Decomposable Submodular Function Minimization","arxiv_id":"1806.09842","date":"2018-06-26","proceeding":"NeurIPS 2018 12","authors":["Pan Li","Niao He","Olgica Milenkovic"],"abstract":"We introduce a new convex optimization problem, termed quadratic decomposable\nsubmodular function minimization. The problem is closely related to\ndecomposable submodular function minimization and arises in many learning on\ngraphs and hypergraphs settings, such as graph-based semi-supervised learning\nand PageRank. We approach the problem via a new dual strategy and describe an\nobjective that may be optimized via random coordinate descent (RCD) methods and\nprojections onto cones. We also establish the linear convergence rate of the\nRCD algorithm and develop efficient projection algorithms with provable\nperformance guarantees. Numerical experiments in semi-supervised learning on\nhypergraphs confirm the efficiency of the proposed algorithm and demonstrate\nthe significant improvements in prediction accuracy with respect to\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1806.09842v3","url_pdf":"http://arxiv.org/pdf/1806.09842v3.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":"quadratic-decomposable-submodular-function","repo_url":"https://github.com/lipan00123/QDSDM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}