{"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/beyond-alternating-updates-for-matrix","title":"Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms","arxiv_id":"1905.09050","date":"2019-05-22","proceeding":"NeurIPS 2019 12","authors":["Mahesh Chandra Mukkamala","Peter Ochs"],"abstract":"Matrix Factorization is a popular non-convex optimization problem, for which alternating minimization schemes are mostly used. They usually suffer from the major drawback that the solution is biased towards one of the optimization variables. A remedy is non-alternating schemes. However, due to a lack of Lipschitz continuity of the gradient in matrix factorization problems, convergence cannot be guaranteed. A recently developed approach relies on the concept of Bregman distances, which generalizes the standard Euclidean distance. We exploit this theory by proposing a novel Bregman distance for matrix factorization problems, which, at the same time, allows for simple/closed form update steps. Therefore, for non-alternating schemes, such as the recently introduced Bregman Proximal Gradient (BPG) method and an inertial variant Convex--Concave Inertial BPG (CoCaIn BPG), convergence of the whole sequence to a stationary point is proved for Matrix Factorization. In several experiments, we observe a superior performance of our non-alternating schemes in terms of speed and objective value at the limit point.","url_abs":"https://arxiv.org/abs/1905.09050v2","url_pdf":"https://arxiv.org/pdf/1905.09050v2.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":"beyond-alternating-updates-for-matrix","repo_url":"https://github.com/mmahesh/cocain-bpg-matrix-completion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-alternating-updates-for-matrix","repo_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.09050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09050"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/mmahesh/cocain-bpg-matrix-factorization","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mmahesh/cocain-bpg-matrix-completion","reach":null}],"summary":{"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":2}},"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":"cd198438e27f36b2","entry":"loss_func1","repo":"mmahesh/cocain-bpg-matrix-completion","repo_kind":"listed","path":"matrix_completion_pytorch.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-completion/blob/HEAD/matrix_completion_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cd198438e27f36b2"}},{"code_sha256_prefix":"91b70c2f20574c88","entry":"abs_func","repo":"mmahesh/cocain-bpg-matrix-factorization","repo_kind":"listed","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/my_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"91b70c2f20574c88"}},{"code_sha256_prefix":"dfebed255091bcc7","entry":"do_tight_layout_for_fig","repo":"mmahesh/cocain-bpg-matrix-factorization","repo_kind":"listed","path":"create_plots.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/create_plots.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dfebed255091bcc7"}},{"code_sha256_prefix":"7de0fb631a5ab4ea","entry":"grad","repo":"mmahesh/cocain-bpg-matrix-factorization","repo_kind":"listed","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/my_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7de0fb631a5ab4ea"}},{"code_sha256_prefix":"200fbb5b8e7f0382","entry":"main_func","repo":"mmahesh/cocain-bpg-matrix-factorization","repo_kind":"listed","path":"my_functions.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/my_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"200fbb5b8e7f0382"}},{"code_sha256_prefix":"a4a5a170457994fe","entry":"makeup_for_plot","repo":"mmahesh/cocain-bpg-matrix-factorization","repo_kind":"listed","path":"create_plots.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-factorization/blob/HEAD/create_plots.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a4a5a170457994fe"}},{"code_sha256_prefix":"d6dd9c2a3f968978","entry":"train_test_split2","repo":"mmahesh/cocain-bpg-matrix-completion","repo_kind":"listed","path":"create_datasets.py","file_url":"https://github.com/mmahesh/cocain-bpg-matrix-completion/blob/HEAD/create_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d6dd9c2a3f968978"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}