{"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/an-accelerated-communication-efficient-primal","title":"An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning","arxiv_id":"1711.05305","date":"2017-11-14","proceeding":null,"authors":["Chenxin Ma","Martin Jaggi","Frank E. Curtis","Nathan Srebro","Martin Takáč"],"abstract":"Distributed optimization algorithms are essential for training machine\nlearning models on very large-scale datasets. However, they often suffer from\ncommunication bottlenecks. Confronting this issue, a communication-efficient\nprimal-dual coordinate ascent framework (CoCoA) and its improved variant CoCoA+\nhave been proposed, achieving a convergence rate of $\\mathcal{O}(1/t)$ for\nsolving empirical risk minimization problems with Lipschitz continuous losses.\nIn this paper, an accelerated variant of CoCoA+ is proposed and shown to\npossess a convergence rate of $\\mathcal{O}(1/t^2)$ in terms of reducing\nsuboptimality. The analysis of this rate is also notable in that the\nconvergence rate bounds involve constants that, except in extreme cases, are\nsignificantly reduced compared to those previously provided for CoCoA+. The\nresults of numerical experiments are provided to show that acceleration can\nlead to significant performance gains.","url_abs":"http://arxiv.org/abs/1711.05305v1","url_pdf":"http://arxiv.org/pdf/1711.05305v1.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":"an-accelerated-communication-efficient-primal","repo_url":"https://github.com/schemmy/CoCoA-Experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"distributed-optimization","task_name":"Distributed Optimization"}],"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}