{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DYQXAXNXFU7LINJZTF4DKRMAGR","short_pith_number":"pith:DYQXAXNX","schema_version":"1.0","canonical_sha256":"1e21705db72d3eb4353999783545803440b7a6ddbfa67e10e3efebd72cd38a7e","source":{"kind":"arxiv","id":"1908.02246","version":1},"attestation_state":"computed","paper":{"title":"On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Ping Li, Xiao-Tong Yuan","submitted_at":"2019-08-06T16:36:30Z","abstract_excerpt":"The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and versatility. Convergence of DANE, however, can be tricky; its appealing convergence rate is only rigorous for quadratic objective, and for more general convex functions the known results are no stronger than those of the classic first-order methods. To remedy these drawbacks, we propose in this paper some new alternatives of DANE which are more suitable for analysis. We first introduce a simple variant of DANE equip"},"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":"1908.02246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-06T16:36:30Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"5ec3b3c0f5f6f00366ff524258c60a72b43959b464808ec2a98a46ebf49a4989","abstract_canon_sha256":"add9a17ac306eb2a96c6777c68a9ad918f0ebd3c062c7feb45d7a0cb72efdcc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:52.385020Z","signature_b64":"g2o1mqkgwYWNUYtfpCcW1PhxlsE6IQUh7JDToVKmoXp+fkxwM14V7e8CP20zGWPAePffTQUgumXQdaP4cWIjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e21705db72d3eb4353999783545803440b7a6ddbfa67e10e3efebd72cd38a7e","last_reissued_at":"2026-07-04T23:51:52.384690Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:52.384690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Ping Li, Xiao-Tong Yuan","submitted_at":"2019-08-06T16:36:30Z","abstract_excerpt":"The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and versatility. Convergence of DANE, however, can be tricky; its appealing convergence rate is only rigorous for quadratic objective, and for more general convex functions the known results are no stronger than those of the classic first-order methods. To remedy these drawbacks, we propose in this paper some new alternatives of DANE which are more suitable for analysis. We first introduce a simple variant of DANE equip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02246","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/1908.02246/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":"1908.02246","created_at":"2026-07-04T23:51:52.384746+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02246v1","created_at":"2026-07-04T23:51:52.384746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02246","created_at":"2026-07-04T23:51:52.384746+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYQXAXNXFU7L","created_at":"2026-07-04T23:51:52.384746+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYQXAXNXFU7LINJZ","created_at":"2026-07-04T23:51:52.384746+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYQXAXNX","created_at":"2026-07-04T23:51:52.384746+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/DYQXAXNXFU7LINJZTF4DKRMAGR","json":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR.json","graph_json":"https://pith.science/api/pith-number/DYQXAXNXFU7LINJZTF4DKRMAGR/graph.json","events_json":"https://pith.science/api/pith-number/DYQXAXNXFU7LINJZTF4DKRMAGR/events.json","paper":"https://pith.science/paper/DYQXAXNX"},"agent_actions":{"view_html":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR","download_json":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR.json","view_paper":"https://pith.science/paper/DYQXAXNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02246&json=true","fetch_graph":"https://pith.science/api/pith-number/DYQXAXNXFU7LINJZTF4DKRMAGR/graph.json","fetch_events":"https://pith.science/api/pith-number/DYQXAXNXFU7LINJZTF4DKRMAGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR/action/storage_attestation","attest_author":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR/action/author_attestation","sign_citation":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR/action/citation_signature","submit_replication":"https://pith.science/pith/DYQXAXNXFU7LINJZTF4DKRMAGR/action/replication_record"}},"created_at":"2026-07-04T23:51:52.384746+00:00","updated_at":"2026-07-04T23:51:52.384746+00:00"}