{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VJXIVSSCCX4RYWPOV3BR377CYR","short_pith_number":"pith:VJXIVSSC","schema_version":"1.0","canonical_sha256":"aa6e8aca4215f91c59eeaec31dffe2c460833cf885109790b8519c3139432db9","source":{"kind":"arxiv","id":"2409.15955","version":5},"attestation_state":"computed","paper":{"title":"A Historical Trajectory Assisted Optimization Method for Zeroth-Order Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenlin Wu, Jing Gong, Xiaoyu He, Zibin Zheng, Zike Li","submitted_at":"2024-09-24T10:36:40Z","abstract_excerpt":"Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve the gradient estimation procedure. Gradients in our method are estimated in a subspace"},"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":"2409.15955","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T10:36:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7a35c7879bd4d4536fcc971dba82f6e181de68536a934f9a67627a5d8f75730","abstract_canon_sha256":"e27ea51b0ba7b0432f8270821aebe14d4efea4cda41812ece3f27e369dda9323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:01.554902Z","signature_b64":"7rIGlC48NjBg/Wlnl7/Kf3xtHwSIuIHkmbKUx3i2jpO32G/uan0X67PXra0O4GB2e3TsPiCdNXnMoaHjFzxOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa6e8aca4215f91c59eeaec31dffe2c460833cf885109790b8519c3139432db9","last_reissued_at":"2026-07-05T09:25:01.554448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:01.554448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Historical Trajectory Assisted Optimization Method for Zeroth-Order Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenlin Wu, Jing Gong, Xiaoyu He, Zibin Zheng, Zike Li","submitted_at":"2024-09-24T10:36:40Z","abstract_excerpt":"Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve the gradient estimation procedure. Gradients in our method are estimated in a subspace"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15955","kind":"arxiv","version":5},"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/2409.15955/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":"2409.15955","created_at":"2026-07-05T09:25:01.554504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15955v5","created_at":"2026-07-05T09:25:01.554504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15955","created_at":"2026-07-05T09:25:01.554504+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJXIVSSCCX4R","created_at":"2026-07-05T09:25:01.554504+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJXIVSSCCX4RYWPO","created_at":"2026-07-05T09:25:01.554504+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJXIVSSC","created_at":"2026-07-05T09:25:01.554504+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/VJXIVSSCCX4RYWPOV3BR377CYR","json":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR.json","graph_json":"https://pith.science/api/pith-number/VJXIVSSCCX4RYWPOV3BR377CYR/graph.json","events_json":"https://pith.science/api/pith-number/VJXIVSSCCX4RYWPOV3BR377CYR/events.json","paper":"https://pith.science/paper/VJXIVSSC"},"agent_actions":{"view_html":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR","download_json":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR.json","view_paper":"https://pith.science/paper/VJXIVSSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15955&json=true","fetch_graph":"https://pith.science/api/pith-number/VJXIVSSCCX4RYWPOV3BR377CYR/graph.json","fetch_events":"https://pith.science/api/pith-number/VJXIVSSCCX4RYWPOV3BR377CYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR/action/storage_attestation","attest_author":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR/action/author_attestation","sign_citation":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR/action/citation_signature","submit_replication":"https://pith.science/pith/VJXIVSSCCX4RYWPOV3BR377CYR/action/replication_record"}},"created_at":"2026-07-05T09:25:01.554504+00:00","updated_at":"2026-07-05T09:25:01.554504+00:00"}