{"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/fast-and-sample-efficient-inductive-matrix","title":"Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow","arxiv_id":"1803.01233","date":"2018-03-03","proceeding":"ICML 2018 7","authors":["Xiao Zhang","Simon S. Du","Quanquan Gu"],"abstract":"We revisit the inductive matrix completion problem that aims to recover a\nrank-$r$ matrix with ambient dimension $d$ given $n$ features as the side prior\ninformation. The goal is to make use of the known $n$ features to reduce sample\nand computational complexities. We present and analyze a new gradient-based\nnon-convex optimization algorithm that converges to the true underlying matrix\nat a linear rate with sample complexity only linearly depending on $n$ and\nlogarithmically depending on $d$. To the best of our knowledge, all previous\nalgorithms either have a quadratic dependency on the number of features in\nsample complexity or a sub-linear computational convergence rate. In addition,\nwe provide experiments on both synthetic and real world data to demonstrate the\neffectiveness of our proposed algorithm.","url_abs":"http://arxiv.org/abs/1803.01233v1","url_pdf":"http://arxiv.org/pdf/1803.01233v1.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":"fast-and-sample-efficient-inductive-matrix","repo_url":"https://github.com/xiaozhanguva/inductive-mc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"matrix-completion","task_name":"Matrix Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}