{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LIAYPMJBVZUP53A4YUK4IQPFO7","short_pith_number":"pith:LIAYPMJB","schema_version":"1.0","canonical_sha256":"5a0187b121ae68feec1cc515c441e577c355df846b0dc804ea34d4156f96216d","source":{"kind":"arxiv","id":"1711.05305","version":1},"attestation_state":"computed","paper":{"title":"An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Chenxin Ma, Frank E. Curtis, Martin Jaggi, Martin Tak\\'a\\v{c}, Nathan Srebro","submitted_at":"2017-11-14T20:19:10Z","abstract_excerpt":"Distributed optimization algorithms are essential for training machine learning models on very large-scale datasets. However, they often suffer from communication bottlenecks. Confronting this issue, a communication-efficient primal-dual coordinate ascent framework (CoCoA) and its improved variant CoCoA+ have been proposed, achieving a convergence rate of $\\mathcal{O}(1/t)$ for solving empirical risk minimization problems with Lipschitz continuous losses. In this paper, an accelerated variant of CoCoA+ is proposed and shown to possess a convergence rate of $\\mathcal{O}(1/t^2)$ in terms of redu"},"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":"1711.05305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-11-14T20:19:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a32d990551a5677ae24dbc80edfc120aa37bbb97a7de05c36cf9f2842ec9296","abstract_canon_sha256":"37efc9c4f3d6c9d1335741039be0d00c3a32e63fb04098030eea7a850b2841c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:33.695405Z","signature_b64":"QmKwiVQ/01BAo+ZIW9jibtjMwNu1qgs3/Zwz/bI6OXebRGmsTJWIQPs9n0K1nPX8F0O9N5LExvLsYLxJbRESCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0187b121ae68feec1cc515c441e577c355df846b0dc804ea34d4156f96216d","last_reissued_at":"2026-05-18T00:30:33.694792Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:33.694792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Chenxin Ma, Frank E. Curtis, Martin Jaggi, Martin Tak\\'a\\v{c}, Nathan Srebro","submitted_at":"2017-11-14T20:19:10Z","abstract_excerpt":"Distributed optimization algorithms are essential for training machine learning models on very large-scale datasets. However, they often suffer from communication bottlenecks. Confronting this issue, a communication-efficient primal-dual coordinate ascent framework (CoCoA) and its improved variant CoCoA+ have been proposed, achieving a convergence rate of $\\mathcal{O}(1/t)$ for solving empirical risk minimization problems with Lipschitz continuous losses. In this paper, an accelerated variant of CoCoA+ is proposed and shown to possess a convergence rate of $\\mathcal{O}(1/t^2)$ in terms of redu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05305","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.05305","created_at":"2026-05-18T00:30:33.694864+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05305v1","created_at":"2026-05-18T00:30:33.694864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05305","created_at":"2026-05-18T00:30:33.694864+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIAYPMJBVZUP","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIAYPMJBVZUP53A4","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIAYPMJB","created_at":"2026-05-18T12:31:28.150371+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/LIAYPMJBVZUP53A4YUK4IQPFO7","json":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7.json","graph_json":"https://pith.science/api/pith-number/LIAYPMJBVZUP53A4YUK4IQPFO7/graph.json","events_json":"https://pith.science/api/pith-number/LIAYPMJBVZUP53A4YUK4IQPFO7/events.json","paper":"https://pith.science/paper/LIAYPMJB"},"agent_actions":{"view_html":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7","download_json":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7.json","view_paper":"https://pith.science/paper/LIAYPMJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05305&json=true","fetch_graph":"https://pith.science/api/pith-number/LIAYPMJBVZUP53A4YUK4IQPFO7/graph.json","fetch_events":"https://pith.science/api/pith-number/LIAYPMJBVZUP53A4YUK4IQPFO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7/action/storage_attestation","attest_author":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7/action/author_attestation","sign_citation":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7/action/citation_signature","submit_replication":"https://pith.science/pith/LIAYPMJBVZUP53A4YUK4IQPFO7/action/replication_record"}},"created_at":"2026-05-18T00:30:33.694864+00:00","updated_at":"2026-05-18T00:30:33.694864+00:00"}