{"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/communication-avoiding-optimization-methods","title":"Communication-Avoiding Optimization Methods for Distributed Massive-Scale Sparse Inverse Covariance Estimation","arxiv_id":"1710.10769","date":"2017-10-30","proceeding":null,"authors":["Penporn Koanantakool","Alnur Ali","Ariful Azad","Aydin Buluc","Dmitriy Morozov","Leonid Oliker","Katherine Yelick","Sang-Yun Oh"],"abstract":"Across a variety of scientific disciplines, sparse inverse covariance\nestimation is a popular tool for capturing the underlying dependency\nrelationships in multivariate data. Unfortunately, most estimators are not\nscalable enough to handle the sizes of modern high-dimensional data sets (often\non the order of terabytes), and assume Gaussian samples. To address these\ndeficiencies, we introduce HP-CONCORD, a highly scalable optimization method\nfor estimating a sparse inverse covariance matrix based on a regularized\npseudolikelihood framework, without assuming Gaussianity. Our parallel proximal\ngradient method uses a novel communication-avoiding linear algebra algorithm\nand runs across a multi-node cluster with up to 1k nodes (24k cores), achieving\nparallel scalability on problems with up to ~819 billion parameters (1.28\nmillion dimensions); even on a single node, HP-CONCORD demonstrates\nscalability, outperforming a state-of-the-art method. We also use HP-CONCORD to\nestimate the underlying dependency structure of the brain from fMRI data, and\nuse the result to identify functional regions automatically. The results show\ngood agreement with a clustering from the neuroscience literature.","url_abs":"http://arxiv.org/abs/1710.10769v2","url_pdf":"http://arxiv.org/pdf/1710.10769v2.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":"communication-avoiding-optimization-methods","repo_url":"https://bitbucket.org/penpornk/spdm3-hpconcord","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.10769","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}