{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:333CSJRHYJ5VDTPASEBM4PNDIG","short_pith_number":"pith:333CSJRH","schema_version":"1.0","canonical_sha256":"def6292627c27b51cde09102ce3da3419cced048f715fa63959bafdd48f99ec0","source":{"kind":"arxiv","id":"2502.00470","version":3},"attestation_state":"computed","paper":{"title":"On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andi Wang, Runxiong Wu","submitted_at":"2025-02-01T15:56:11Z","abstract_excerpt":"Distributed empirical risk minimization (ERM) is often studied through two influential yet seemingly separate families of methods: CoCoA-type algorithms, derived from distributed dual coordinate ascent, and ADMM-type algorithms, derived from consensus and proximal splitting. In this paper, we investigate the connection of the two types of algorithms from a unified primal-dual perspective. We show that consensus ADMM, linearized consensus ADMM, two distributed proximal ADMM variants, and ridge-regularized CoCoA can all be written in a common update form involving a global primal variable and bl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.00470","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-01T15:56:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fd27a757c3da6e885cf610c9ec5268ce0f6bcda6d25fa7344dda2b6a3765ff1a","abstract_canon_sha256":"dc1f6f8fc3a132e83500106bd157f85a35b263f849e4ca9820f12e8bec2ef6db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:27.418585Z","signature_b64":"PSm/EpiGJMKQ5UwHkwEUJThTeIDsCIDTkZRWyTbwUVHSwSVZLSxn5YabttOm5X3260Z3AdwYAbf2eWCd492RBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def6292627c27b51cde09102ce3da3419cced048f715fa63959bafdd48f99ec0","last_reissued_at":"2026-06-04T01:08:27.417643Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:27.417643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andi Wang, Runxiong Wu","submitted_at":"2025-02-01T15:56:11Z","abstract_excerpt":"Distributed empirical risk minimization (ERM) is often studied through two influential yet seemingly separate families of methods: CoCoA-type algorithms, derived from distributed dual coordinate ascent, and ADMM-type algorithms, derived from consensus and proximal splitting. In this paper, we investigate the connection of the two types of algorithms from a unified primal-dual perspective. We show that consensus ADMM, linearized consensus ADMM, two distributed proximal ADMM variants, and ridge-regularized CoCoA can all be written in a common update form involving a global primal variable and bl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00470","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.00470/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.00470","created_at":"2026-06-04T01:08:27.417774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00470v3","created_at":"2026-06-04T01:08:27.417774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00470","created_at":"2026-06-04T01:08:27.417774+00:00"},{"alias_kind":"pith_short_12","alias_value":"333CSJRHYJ5V","created_at":"2026-06-04T01:08:27.417774+00:00"},{"alias_kind":"pith_short_16","alias_value":"333CSJRHYJ5VDTPA","created_at":"2026-06-04T01:08:27.417774+00:00"},{"alias_kind":"pith_short_8","alias_value":"333CSJRH","created_at":"2026-06-04T01:08:27.417774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG","json":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG.json","graph_json":"https://pith.science/api/pith-number/333CSJRHYJ5VDTPASEBM4PNDIG/graph.json","events_json":"https://pith.science/api/pith-number/333CSJRHYJ5VDTPASEBM4PNDIG/events.json","paper":"https://pith.science/paper/333CSJRH"},"agent_actions":{"view_html":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG","download_json":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG.json","view_paper":"https://pith.science/paper/333CSJRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00470&json=true","fetch_graph":"https://pith.science/api/pith-number/333CSJRHYJ5VDTPASEBM4PNDIG/graph.json","fetch_events":"https://pith.science/api/pith-number/333CSJRHYJ5VDTPASEBM4PNDIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG/action/storage_attestation","attest_author":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG/action/author_attestation","sign_citation":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG/action/citation_signature","submit_replication":"https://pith.science/pith/333CSJRHYJ5VDTPASEBM4PNDIG/action/replication_record"}},"created_at":"2026-06-04T01:08:27.417774+00:00","updated_at":"2026-06-04T01:08:27.417774+00:00"}