{"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/easily-parallelizable-and-distributable-class","title":"Easily parallelizable and distributable class of algorithms for structured sparsity, with optimal acceleration","arxiv_id":"1702.06234","date":"2017-02-21","proceeding":null,"authors":["Seyoon Ko","Donghyeon Yu","Joong-Ho Won"],"abstract":"Many statistical learning problems can be posed as minimization of a sum of\ntwo convex functions, one typically a composition of non-smooth and linear\nfunctions. Examples include regression under structured sparsity assumptions.\nPopular algorithms for solving such problems, e.g., ADMM, often involve\nnon-trivial optimization subproblems or smoothing approximation. We consider\ntwo classes of primal-dual algorithms that do not incur these difficulties, and\nunify them from a perspective of monotone operator theory. From this\nunification we propose a continuum of preconditioned forward-backward operator\nsplitting algorithms amenable to parallel and distributed computing. For the\nentire region of convergence of the whole continuum of algorithms, we establish\nits rates of convergence. For some known instances of this continuum, our\nanalysis closes the gap in theory. We further exploit the unification to\npropose a continuum of accelerated algorithms. We show that the whole continuum\nattains the theoretically optimal rate of convergence. The scalability of the\nproposed algorithms, as well as their convergence behavior, is demonstrated up\nto 1.2 million variables with a distributed implementation.","url_abs":"http://arxiv.org/abs/1702.06234v3","url_pdf":"http://arxiv.org/pdf/1702.06234v3.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":"easily-parallelizable-and-distributable-class","repo_url":"https://github.com/kose-y/dist-primal-dual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"distributed-computing","task_name":"Distributed Computing"}],"methods":[{"method_slug":"admm","method_name":"ADMM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.06234","atlas_url":"https://app.syntology.ai/?focus=1702.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.06234"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kose-y/dist-primal-dual","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a309ab27e2d25b28","entry":"coo_to_sparsetensor","repo":"kose-y/dist-primal-dual","repo_kind":"listed","path":"dist_pd/utils.py","file_url":"https://github.com/kose-y/dist-primal-dual/blob/HEAD/dist_pd/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a309ab27e2d25b28"}},{"code_sha256_prefix":"d4618f33bd228031","entry":"csr_nonzero_rows","repo":"kose-y/dist-primal-dual","repo_kind":"listed","path":"dist_pd/distmat.py","file_url":"https://github.com/kose-y/dist-primal-dual/blob/HEAD/dist_pd/distmat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4618f33bd228031"}},{"code_sha256_prefix":"e0e4d9b0238dcd44","entry":"default_partitioner","repo":"kose-y/dist-primal-dual","repo_kind":"listed","path":"dist_pd/partitioners.py","file_url":"https://github.com/kose-y/dist-primal-dual/blob/HEAD/dist_pd/partitioners.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0e4d9b0238dcd44"}},{"code_sha256_prefix":"9f7aa7b4ea0da26d","entry":"find_nearest","repo":"kose-y/dist-primal-dual","repo_kind":"listed","path":"dist_pd/utils.py","file_url":"https://github.com/kose-y/dist-primal-dual/blob/HEAD/dist_pd/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f7aa7b4ea0da26d"}},{"code_sha256_prefix":"4fbcb14f299d932b","entry":"gidx_to_partition","repo":"kose-y/dist-primal-dual","repo_kind":"listed","path":"dist_pd/utils.py","file_url":"https://github.com/kose-y/dist-primal-dual/blob/HEAD/dist_pd/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4fbcb14f299d932b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}