{"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/a-constrained-l1-minimization-approach-for","title":"A constrained L1 minimization approach for estimating multiple Sparse Gaussian or Nonparanormal Graphical Models","arxiv_id":"1605.03468","date":"2016-05-11","proceeding":null,"authors":["Beilun Wang","Ritambhara Singh","Yanjun Qi"],"abstract":"Identifying context-specific entity networks from aggregated data is an\nimportant task, arising often in bioinformatics and neuroimaging.\nComputationally, this task can be formulated as jointly estimating multiple\ndifferent, but related, sparse Undirected Graphical Models (UGM) from\naggregated samples across several contexts. Previous joint-UGM studies have\nmostly focused on sparse Gaussian Graphical Models (sGGMs) and can't identify\ncontext-specific edge patterns directly. We, therefore, propose a novel\napproach, SIMULE (detecting Shared and Individual parts of MULtiple graphs\nExplicitly) to learn multi-UGM via a constrained L1 minimization. SIMULE\nautomatically infers both specific edge patterns that are unique to each\ncontext and shared interactions preserved among all the contexts. Through the\nL1 constrained formulation, this problem is cast as multiple independent\nsubtasks of linear programming that can be solved efficiently in parallel. In\naddition to Gaussian data, SIMULE can also handle multivariate Nonparanormal\ndata that greatly relaxes the normality assumption that many real-world\napplications do not follow. We provide a novel theoretical proof showing that\nSIMULE achieves a consistent result at the rate O(log(Kp)/n_{tot}). On multiple\nsynthetic datasets and two biomedical datasets, SIMULE shows significant\nimprovement over state-of-the-art multi-sGGM and single-UGM baselines.","url_abs":"http://arxiv.org/abs/1605.03468v6","url_pdf":"http://arxiv.org/pdf/1605.03468v6.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":"a-constrained-l1-minimization-approach-for","repo_url":"https://github.com/QData/SIMULE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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}