{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:42RD7IBJXV6VQYMZS5Q74VQHCT","short_pith_number":"pith:42RD7IBJ","schema_version":"1.0","canonical_sha256":"e6a23fa029bd7d5861999761fe560714d4e8038479905871415d06732f43dcd5","source":{"kind":"arxiv","id":"1810.01053","version":3},"attestation_state":"computed","paper":{"title":"Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Cong Fang, Huan Li, Wotao Yin, Zhouchen Lin","submitted_at":"2018-10-02T03:38:58Z","abstract_excerpt":"In this paper, we study the communication and (sub)gradient computation costs in distributed optimization and give a sharp complexity analysis for the proposed distributed accelerated gradient methods. We present two algorithms based on the framework of the accelerated penalty method with increasing penalty parameters. Our first algorithm is for smooth distributed optimization and it obtains the near optimal $O\\left(\\sqrt{\\frac{L}{\\epsilon(1-\\sigma_2(W))}}\\log\\frac{1}{\\epsilon}\\right)$ communication complexity and the optimal $O\\left(\\sqrt{\\frac{L}{\\epsilon}}\\right)$ gradient computation compl"},"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":"1810.01053","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-10-02T03:38:58Z","cross_cats_sorted":[],"title_canon_sha256":"900b6bf314ddbec467f74a4dfa3b4b0b48c8e11f1530202b7177539ce748a2a1","abstract_canon_sha256":"f06668b60204ef27c7352be7016470ad016008f23ad45377c5cc1e4d86964ea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:41.545922Z","signature_b64":"ohnakg0Rhs65aY/EMAHp3j6VSkYmXj+bjbU0xyr/3OQXHwSozmfqBaV4BO3bwmEeMMD/bbbmrrL8XBmWdCXcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a23fa029bd7d5861999761fe560714d4e8038479905871415d06732f43dcd5","last_reissued_at":"2026-07-05T01:27:41.545205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:41.545205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Cong Fang, Huan Li, Wotao Yin, Zhouchen Lin","submitted_at":"2018-10-02T03:38:58Z","abstract_excerpt":"In this paper, we study the communication and (sub)gradient computation costs in distributed optimization and give a sharp complexity analysis for the proposed distributed accelerated gradient methods. We present two algorithms based on the framework of the accelerated penalty method with increasing penalty parameters. Our first algorithm is for smooth distributed optimization and it obtains the near optimal $O\\left(\\sqrt{\\frac{L}{\\epsilon(1-\\sigma_2(W))}}\\log\\frac{1}{\\epsilon}\\right)$ communication complexity and the optimal $O\\left(\\sqrt{\\frac{L}{\\epsilon}}\\right)$ gradient computation compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01053","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/1810.01053/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":"1810.01053","created_at":"2026-07-05T01:27:41.545343+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01053v3","created_at":"2026-07-05T01:27:41.545343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01053","created_at":"2026-07-05T01:27:41.545343+00:00"},{"alias_kind":"pith_short_12","alias_value":"42RD7IBJXV6V","created_at":"2026-07-05T01:27:41.545343+00:00"},{"alias_kind":"pith_short_16","alias_value":"42RD7IBJXV6VQYMZ","created_at":"2026-07-05T01:27:41.545343+00:00"},{"alias_kind":"pith_short_8","alias_value":"42RD7IBJ","created_at":"2026-07-05T01:27:41.545343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07496","citing_title":"Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT","json":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT.json","graph_json":"https://pith.science/api/pith-number/42RD7IBJXV6VQYMZS5Q74VQHCT/graph.json","events_json":"https://pith.science/api/pith-number/42RD7IBJXV6VQYMZS5Q74VQHCT/events.json","paper":"https://pith.science/paper/42RD7IBJ"},"agent_actions":{"view_html":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT","download_json":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT.json","view_paper":"https://pith.science/paper/42RD7IBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01053&json=true","fetch_graph":"https://pith.science/api/pith-number/42RD7IBJXV6VQYMZS5Q74VQHCT/graph.json","fetch_events":"https://pith.science/api/pith-number/42RD7IBJXV6VQYMZS5Q74VQHCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT/action/storage_attestation","attest_author":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT/action/author_attestation","sign_citation":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT/action/citation_signature","submit_replication":"https://pith.science/pith/42RD7IBJXV6VQYMZS5Q74VQHCT/action/replication_record"}},"created_at":"2026-07-05T01:27:41.545343+00:00","updated_at":"2026-07-05T01:27:41.545343+00:00"}