{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E2UWDPVSSWGKBQ4S6TLCOFVDYN","short_pith_number":"pith:E2UWDPVS","schema_version":"1.0","canonical_sha256":"26a961beb2958ca0c392f4d62716a3c3627c8cc0e71bd23e6e1fe927d985db37","source":{"kind":"arxiv","id":"2302.04969","version":3},"attestation_state":"computed","paper":{"title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiyi Ji, Peiyao Xiao","submitted_at":"2023-02-09T23:07:34Z","abstract_excerpt":"Federated bilevel optimization has attracted increasing attention due to emerging machine learning and communication applications. The biggest challenge lies in computing the gradient of the upper-level objective function (i.e., hypergradient) in the federated setting due to the nonlinear and distributed construction of a series of global Hessian matrices. In this paper, we propose a novel communication-efficient federated hypergradient estimator via aggregated iterative differentiation (AggITD). AggITD is simple to implement and significantly reduces the communication cost by conducting the f"},"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":"2302.04969","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T23:07:34Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"94d17c53ed3a882ac8779a2c90bf19e8a53e415362f6a9324c83fde0c78167a0","abstract_canon_sha256":"35049bfb5db10ac6aa36158d42c0db2bf1e3541d538662bdd31e3d3d3fc27b99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:15.546105Z","signature_b64":"3fmQRb2mFrC1ukioPxj8+Gh1hSG1ZUW59x7hLSnI9r837tzUBU6Y6clv6wY/fWXLl/u8h9mtEOcRJgCHv5f6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a961beb2958ca0c392f4d62716a3c3627c8cc0e71bd23e6e1fe927d985db37","last_reissued_at":"2026-07-05T06:21:15.545615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:15.545615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiyi Ji, Peiyao Xiao","submitted_at":"2023-02-09T23:07:34Z","abstract_excerpt":"Federated bilevel optimization has attracted increasing attention due to emerging machine learning and communication applications. The biggest challenge lies in computing the gradient of the upper-level objective function (i.e., hypergradient) in the federated setting due to the nonlinear and distributed construction of a series of global Hessian matrices. In this paper, we propose a novel communication-efficient federated hypergradient estimator via aggregated iterative differentiation (AggITD). AggITD is simple to implement and significantly reduces the communication cost by conducting the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04969","kind":"arxiv","version":3},"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/2302.04969/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":"2302.04969","created_at":"2026-07-05T06:21:15.545683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04969v3","created_at":"2026-07-05T06:21:15.545683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04969","created_at":"2026-07-05T06:21:15.545683+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2UWDPVSSWGK","created_at":"2026-07-05T06:21:15.545683+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2UWDPVSSWGKBQ4S","created_at":"2026-07-05T06:21:15.545683+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2UWDPVS","created_at":"2026-07-05T06:21:15.545683+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/E2UWDPVSSWGKBQ4S6TLCOFVDYN","json":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN.json","graph_json":"https://pith.science/api/pith-number/E2UWDPVSSWGKBQ4S6TLCOFVDYN/graph.json","events_json":"https://pith.science/api/pith-number/E2UWDPVSSWGKBQ4S6TLCOFVDYN/events.json","paper":"https://pith.science/paper/E2UWDPVS"},"agent_actions":{"view_html":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN","download_json":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN.json","view_paper":"https://pith.science/paper/E2UWDPVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04969&json=true","fetch_graph":"https://pith.science/api/pith-number/E2UWDPVSSWGKBQ4S6TLCOFVDYN/graph.json","fetch_events":"https://pith.science/api/pith-number/E2UWDPVSSWGKBQ4S6TLCOFVDYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN/action/storage_attestation","attest_author":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN/action/author_attestation","sign_citation":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN/action/citation_signature","submit_replication":"https://pith.science/pith/E2UWDPVSSWGKBQ4S6TLCOFVDYN/action/replication_record"}},"created_at":"2026-07-05T06:21:15.545683+00:00","updated_at":"2026-07-05T06:21:15.545683+00:00"}