{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TTPCG5BOURTKC7PKTYW4DYD4UL","short_pith_number":"pith:TTPCG5BO","schema_version":"1.0","canonical_sha256":"9cde23742ea466a17dea9e2dc1e07ca2d604a792cb36668c79a8b06c8efb1fc7","source":{"kind":"arxiv","id":"2108.04448","version":2},"attestation_state":"computed","paper":{"title":"Decentralized Composite Optimization with Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Jiliang Tang, Kun Yuan, Ming Yan, Xiaorui Liu, Yao Li","submitted_at":"2021-08-10T04:54:52Z","abstract_excerpt":"Decentralized optimization and communication compression have exhibited their great potential in accelerating distributed machine learning by mitigating the communication bottleneck in practice. While existing decentralized algorithms with communication compression mostly focus on the problems with only smooth components, we study the decentralized stochastic composite optimization problem with a potentially non-smooth component. A \\underline{Prox}imal gradient \\underline{L}in\\underline{EA}r convergent \\underline{D}ecentralized algorithm with compression, Prox-LEAD, is proposed with rigorous t"},"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":"2108.04448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-10T04:54:52Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"8a3bad1455401129c35278c96a4ce5e83d4e763a5b44b94d8dbc44686463353d","abstract_canon_sha256":"ec699723baff5de4332034cba6ef8989142c4c6e7c67f21968f3a819b72f8541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:13.832436Z","signature_b64":"OvQJaHw/oiHv6MJl/CreBtloiVtVWR6/qlfKbjLNGderNvGd/wxOMym/T8Bv3WixXvL3GZBB5v2r0aC577iaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cde23742ea466a17dea9e2dc1e07ca2d604a792cb36668c79a8b06c8efb1fc7","last_reissued_at":"2026-07-05T03:05:13.832077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:13.832077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Composite Optimization with Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Jiliang Tang, Kun Yuan, Ming Yan, Xiaorui Liu, Yao Li","submitted_at":"2021-08-10T04:54:52Z","abstract_excerpt":"Decentralized optimization and communication compression have exhibited their great potential in accelerating distributed machine learning by mitigating the communication bottleneck in practice. While existing decentralized algorithms with communication compression mostly focus on the problems with only smooth components, we study the decentralized stochastic composite optimization problem with a potentially non-smooth component. A \\underline{Prox}imal gradient \\underline{L}in\\underline{EA}r convergent \\underline{D}ecentralized algorithm with compression, Prox-LEAD, is proposed with rigorous t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04448","kind":"arxiv","version":2},"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/2108.04448/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":"2108.04448","created_at":"2026-07-05T03:05:13.832133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04448v2","created_at":"2026-07-05T03:05:13.832133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04448","created_at":"2026-07-05T03:05:13.832133+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTPCG5BOURTK","created_at":"2026-07-05T03:05:13.832133+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTPCG5BOURTKC7PK","created_at":"2026-07-05T03:05:13.832133+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTPCG5BO","created_at":"2026-07-05T03:05:13.832133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01755","citing_title":"Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13054","citing_title":"Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL","json":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL.json","graph_json":"https://pith.science/api/pith-number/TTPCG5BOURTKC7PKTYW4DYD4UL/graph.json","events_json":"https://pith.science/api/pith-number/TTPCG5BOURTKC7PKTYW4DYD4UL/events.json","paper":"https://pith.science/paper/TTPCG5BO"},"agent_actions":{"view_html":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL","download_json":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL.json","view_paper":"https://pith.science/paper/TTPCG5BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04448&json=true","fetch_graph":"https://pith.science/api/pith-number/TTPCG5BOURTKC7PKTYW4DYD4UL/graph.json","fetch_events":"https://pith.science/api/pith-number/TTPCG5BOURTKC7PKTYW4DYD4UL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL/action/storage_attestation","attest_author":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL/action/author_attestation","sign_citation":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL/action/citation_signature","submit_replication":"https://pith.science/pith/TTPCG5BOURTKC7PKTYW4DYD4UL/action/replication_record"}},"created_at":"2026-07-05T03:05:13.832133+00:00","updated_at":"2026-07-05T03:05:13.832133+00:00"}