{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQFOLOCU3KS62323GEF6DQZHDI","short_pith_number":"pith:DQFOLOCU","schema_version":"1.0","canonical_sha256":"1c0ae5b854daa5ed6f5b310be1c3271a2ae8973441b4d689e76113d68ac49204","source":{"kind":"arxiv","id":"2403.01322","version":1},"attestation_state":"computed","paper":{"title":"A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Antai Xie, Ming Cao, Xiaofan Wang, Xiaoqiang Ren, Xinlei Yi","submitted_at":"2024-03-02T21:54:36Z","abstract_excerpt":"This paper studies distributed nonconvex optimization problems with stochastic gradients for a multi-agent system, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed information exchange. We propose a distributed stochastic gradient descent (SGD) algorithm, suitable for a general class of compressors. We show that the proposed algorithm achieves the linear speedup convergence rate $\\mathcal{O}(1/\\sqrt{nT})$ for smooth nonconvex functions, where $T$ and $n$ are the number of iterations and agents, respectively. If the global cost function additi"},"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":"2403.01322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-03-02T21:54:36Z","cross_cats_sorted":[],"title_canon_sha256":"81c58d7a0538788ed1c0a2329cd79218fd4f1c0bfc24116af5426fc1665cf9d0","abstract_canon_sha256":"cce34dbe4411dc6bce8c436b096adcc5dbdcafd4c68a03b0448df7cdda84180b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:45.311307Z","signature_b64":"CNNa3mai1wwP5B7wMJ/d9fBzXm9FFuOJuavgJaJa/8ZdST8ycprktrc/SQklEoAm6G9LmVA4/UQzsf8jPH8RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c0ae5b854daa5ed6f5b310be1c3271a2ae8973441b4d689e76113d68ac49204","last_reissued_at":"2026-07-05T07:51:45.310827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:45.310827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Antai Xie, Ming Cao, Xiaofan Wang, Xiaoqiang Ren, Xinlei Yi","submitted_at":"2024-03-02T21:54:36Z","abstract_excerpt":"This paper studies distributed nonconvex optimization problems with stochastic gradients for a multi-agent system, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed information exchange. We propose a distributed stochastic gradient descent (SGD) algorithm, suitable for a general class of compressors. We show that the proposed algorithm achieves the linear speedup convergence rate $\\mathcal{O}(1/\\sqrt{nT})$ for smooth nonconvex functions, where $T$ and $n$ are the number of iterations and agents, respectively. If the global cost function additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01322","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.01322/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":"2403.01322","created_at":"2026-07-05T07:51:45.310888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01322v1","created_at":"2026-07-05T07:51:45.310888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01322","created_at":"2026-07-05T07:51:45.310888+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQFOLOCU3KS6","created_at":"2026-07-05T07:51:45.310888+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQFOLOCU3KS62323","created_at":"2026-07-05T07:51:45.310888+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQFOLOCU","created_at":"2026-07-05T07:51:45.310888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08964","citing_title":"Decentralized Stochastic Optimization over Unreliable Networks via Two-timescales Updates","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI","json":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI.json","graph_json":"https://pith.science/api/pith-number/DQFOLOCU3KS62323GEF6DQZHDI/graph.json","events_json":"https://pith.science/api/pith-number/DQFOLOCU3KS62323GEF6DQZHDI/events.json","paper":"https://pith.science/paper/DQFOLOCU"},"agent_actions":{"view_html":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI","download_json":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI.json","view_paper":"https://pith.science/paper/DQFOLOCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01322&json=true","fetch_graph":"https://pith.science/api/pith-number/DQFOLOCU3KS62323GEF6DQZHDI/graph.json","fetch_events":"https://pith.science/api/pith-number/DQFOLOCU3KS62323GEF6DQZHDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI/action/storage_attestation","attest_author":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI/action/author_attestation","sign_citation":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI/action/citation_signature","submit_replication":"https://pith.science/pith/DQFOLOCU3KS62323GEF6DQZHDI/action/replication_record"}},"created_at":"2026-07-05T07:51:45.310888+00:00","updated_at":"2026-07-05T07:51:45.310888+00:00"}