{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H3YVUUWRFKMXOB6LNCVO3CEFBA","short_pith_number":"pith:H3YVUUWR","schema_version":"1.0","canonical_sha256":"3ef15a52d12a997707cb68aaed88850820e1e9030f1e0fffa0bf18c35783a1f1","source":{"kind":"arxiv","id":"2602.14830","version":2},"attestation_state":"computed","paper":{"title":"On Convergence Analysis of Network-GIANT: An approximate Hessian-based fully distributed optimization algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SP","eess.SY"],"primary_cat":"math.OC","authors_text":"Luca Schenato, Souvik Das, Subhrakanti Dey","submitted_at":"2026-02-16T15:22:04Z","abstract_excerpt":"This paper presents a detailed convergence and performance analysis of a recently developed approximate Newton-type fully distributed optimization method for \\(L\\)-smooth, \\(\\mu\\)-strongly convex local loss functions, called Network-GIANT (inspired by the Federated learning algorithm GIANT possessing mixed linear-quadratic convergence properties). Network-GIANT has been empirically seen to achieve faster linear convergence properties compared to its gradient-based counterparts, and several other existing second order distributed algorithms, while having the same communication complexity (per i"},"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":"2602.14830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-02-16T15:22:04Z","cross_cats_sorted":["cs.SY","eess.SP","eess.SY"],"title_canon_sha256":"30e7cd6d94476959e1629c9c53a10e6c3b3389cc5237f0a73420556b1b615165","abstract_canon_sha256":"b6cb2c52de97e0f496c28a5dcdcf94ee5579c65eeb6007e2878ef076a3c77b0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:05.798218Z","signature_b64":"67JZ3TBgqDlTv3NNxUtHSd027qwvuTw7Mq+mSYneMc4NXUM2BT9T1Zk7UzVvlAl/rOFJPVDbRrqkT8b/8V8oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef15a52d12a997707cb68aaed88850820e1e9030f1e0fffa0bf18c35783a1f1","last_reissued_at":"2026-07-07T01:16:05.797208Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:05.797208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Convergence Analysis of Network-GIANT: An approximate Hessian-based fully distributed optimization algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SP","eess.SY"],"primary_cat":"math.OC","authors_text":"Luca Schenato, Souvik Das, Subhrakanti Dey","submitted_at":"2026-02-16T15:22:04Z","abstract_excerpt":"This paper presents a detailed convergence and performance analysis of a recently developed approximate Newton-type fully distributed optimization method for \\(L\\)-smooth, \\(\\mu\\)-strongly convex local loss functions, called Network-GIANT (inspired by the Federated learning algorithm GIANT possessing mixed linear-quadratic convergence properties). Network-GIANT has been empirically seen to achieve faster linear convergence properties compared to its gradient-based counterparts, and several other existing second order distributed algorithms, while having the same communication complexity (per i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14830","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/2602.14830/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":"2602.14830","created_at":"2026-07-07T01:16:05.797327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14830v2","created_at":"2026-07-07T01:16:05.797327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14830","created_at":"2026-07-07T01:16:05.797327+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3YVUUWRFKMX","created_at":"2026-07-07T01:16:05.797327+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3YVUUWRFKMXOB6L","created_at":"2026-07-07T01:16:05.797327+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3YVUUWR","created_at":"2026-07-07T01:16:05.797327+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/H3YVUUWRFKMXOB6LNCVO3CEFBA","json":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA.json","graph_json":"https://pith.science/api/pith-number/H3YVUUWRFKMXOB6LNCVO3CEFBA/graph.json","events_json":"https://pith.science/api/pith-number/H3YVUUWRFKMXOB6LNCVO3CEFBA/events.json","paper":"https://pith.science/paper/H3YVUUWR"},"agent_actions":{"view_html":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA","download_json":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA.json","view_paper":"https://pith.science/paper/H3YVUUWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14830&json=true","fetch_graph":"https://pith.science/api/pith-number/H3YVUUWRFKMXOB6LNCVO3CEFBA/graph.json","fetch_events":"https://pith.science/api/pith-number/H3YVUUWRFKMXOB6LNCVO3CEFBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA/action/storage_attestation","attest_author":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA/action/author_attestation","sign_citation":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA/action/citation_signature","submit_replication":"https://pith.science/pith/H3YVUUWRFKMXOB6LNCVO3CEFBA/action/replication_record"}},"created_at":"2026-07-07T01:16:05.797327+00:00","updated_at":"2026-07-07T01:16:05.797327+00:00"}