{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7KF5EVGF2KFG3JMIGOP4UDSKMN","short_pith_number":"pith:7KF5EVGF","schema_version":"1.0","canonical_sha256":"fa8bd254c5d28a6da588339fca0e4a63516cbe1fcf33b237cee583315f083af9","source":{"kind":"arxiv","id":"1902.06101","version":2},"attestation_state":"computed","paper":{"title":"Local Differential Privacy in Decentralized Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"math.OC","authors_text":"Hanshen Xiao, Srinivas Devadas, Yu Ye","submitted_at":"2019-02-16T13:41:35Z","abstract_excerpt":"Privacy concerns with sensitive data are receiving increasing attention. In this paper, we study local differential privacy (LDP) in interactive decentralized optimization. By constructing random local aggregators, we propose a framework to amplify LDP by a constant. We take Alternating Direction Method of Multipliers (ADMM), and decentralized gradient descent as two concrete examples, where experiments support our theory. In an asymptotic view, we address the following question: Under LDP, is it possible to design a distributed private minimizer for arbitrary closed convex constraints with ut"},"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":"1902.06101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-02-16T13:41:35Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"b2ff47c24fe4dbaf9a46185cdd4f3f9ff29ff89cb8afce64e08a97e8f5262b8f","abstract_canon_sha256":"1bf7e206651fe419148b005b31d37c547ebdec09cbba329c43b1ce729de02f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:29.351293Z","signature_b64":"iPRrDTp7II70KaGXWUZUU6MOOhqjiKmAVPxyW6b0N42Gmli+9wwAeHth60rcjytwnZBxOU4bnD+FvrnNIz25CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa8bd254c5d28a6da588339fca0e4a63516cbe1fcf33b237cee583315f083af9","last_reissued_at":"2026-05-17T23:44:29.350626Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:29.350626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Differential Privacy in Decentralized Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"math.OC","authors_text":"Hanshen Xiao, Srinivas Devadas, Yu Ye","submitted_at":"2019-02-16T13:41:35Z","abstract_excerpt":"Privacy concerns with sensitive data are receiving increasing attention. In this paper, we study local differential privacy (LDP) in interactive decentralized optimization. By constructing random local aggregators, we propose a framework to amplify LDP by a constant. We take Alternating Direction Method of Multipliers (ADMM), and decentralized gradient descent as two concrete examples, where experiments support our theory. In an asymptotic view, we address the following question: Under LDP, is it possible to design a distributed private minimizer for arbitrary closed convex constraints with ut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06101","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":""},"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":"1902.06101","created_at":"2026-05-17T23:44:29.350726+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06101v2","created_at":"2026-05-17T23:44:29.350726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06101","created_at":"2026-05-17T23:44:29.350726+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KF5EVGF2KFG","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KF5EVGF2KFG3JMI","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KF5EVGF","created_at":"2026-05-18T12:33:12.712433+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/7KF5EVGF2KFG3JMIGOP4UDSKMN","json":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN.json","graph_json":"https://pith.science/api/pith-number/7KF5EVGF2KFG3JMIGOP4UDSKMN/graph.json","events_json":"https://pith.science/api/pith-number/7KF5EVGF2KFG3JMIGOP4UDSKMN/events.json","paper":"https://pith.science/paper/7KF5EVGF"},"agent_actions":{"view_html":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN","download_json":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN.json","view_paper":"https://pith.science/paper/7KF5EVGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06101&json=true","fetch_graph":"https://pith.science/api/pith-number/7KF5EVGF2KFG3JMIGOP4UDSKMN/graph.json","fetch_events":"https://pith.science/api/pith-number/7KF5EVGF2KFG3JMIGOP4UDSKMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN/action/storage_attestation","attest_author":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN/action/author_attestation","sign_citation":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN/action/citation_signature","submit_replication":"https://pith.science/pith/7KF5EVGF2KFG3JMIGOP4UDSKMN/action/replication_record"}},"created_at":"2026-05-17T23:44:29.350726+00:00","updated_at":"2026-05-17T23:44:29.350726+00:00"}