{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:57HXKCORGPNW4EAGT6DALGJJ6L","short_pith_number":"pith:57HXKCOR","schema_version":"1.0","canonical_sha256":"efcf7509d133db6e10069f86059929f2ef74bb7353ba115ba9e334c78a329076","source":{"kind":"arxiv","id":"2005.07890","version":1},"attestation_state":"computed","paper":{"title":"Differentially Private ADMM for Convex Distributed Learning: Improved Accuracy via Multi-Step Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yanmin Gong, Zonghao Huang","submitted_at":"2020-05-16T07:17:31Z","abstract_excerpt":"Alternating Direction Method of Multipliers (ADMM) is a popular algorithm for distributed learning, where a network of nodes collaboratively solve a regularized empirical risk minimization by iterative local computation associated with distributed data and iterate exchanges. When the training data is sensitive, the exchanged iterates will cause serious privacy concern. In this paper, we aim to propose a new differentially private distributed ADMM algorithm with improved accuracy for a wide range of convex learning problems. In our proposed algorithm, we adopt the approximation of the objective"},"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":"2005.07890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T07:17:31Z","cross_cats_sorted":["cs.CR","cs.DC","stat.ML"],"title_canon_sha256":"4bcd84cb554d3bf7c99e4db8fb2c6f7f2432f71dee91c7ee6b73b7c7798e10b2","abstract_canon_sha256":"34b3c430a0f2a4cf2d081d3ec8a80eea362911ee591ce6259e445c0add014238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:10.943926Z","signature_b64":"7SmK4yPirnVihBQPiyFFoGOf2PdIEnxk56ylWlzalyQmmhto2eTKxJ+E/cHwD9oNytxUaRV7ACn5VVFVfH4ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efcf7509d133db6e10069f86059929f2ef74bb7353ba115ba9e334c78a329076","last_reissued_at":"2026-07-05T01:03:10.943379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:10.943379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private ADMM for Convex Distributed Learning: Improved Accuracy via Multi-Step Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yanmin Gong, Zonghao Huang","submitted_at":"2020-05-16T07:17:31Z","abstract_excerpt":"Alternating Direction Method of Multipliers (ADMM) is a popular algorithm for distributed learning, where a network of nodes collaboratively solve a regularized empirical risk minimization by iterative local computation associated with distributed data and iterate exchanges. When the training data is sensitive, the exchanged iterates will cause serious privacy concern. In this paper, we aim to propose a new differentially private distributed ADMM algorithm with improved accuracy for a wide range of convex learning problems. In our proposed algorithm, we adopt the approximation of the objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07890","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/2005.07890/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":"2005.07890","created_at":"2026-07-05T01:03:10.943442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.07890v1","created_at":"2026-07-05T01:03:10.943442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07890","created_at":"2026-07-05T01:03:10.943442+00:00"},{"alias_kind":"pith_short_12","alias_value":"57HXKCORGPNW","created_at":"2026-07-05T01:03:10.943442+00:00"},{"alias_kind":"pith_short_16","alias_value":"57HXKCORGPNW4EAG","created_at":"2026-07-05T01:03:10.943442+00:00"},{"alias_kind":"pith_short_8","alias_value":"57HXKCOR","created_at":"2026-07-05T01:03:10.943442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04399","citing_title":"DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L","json":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L.json","graph_json":"https://pith.science/api/pith-number/57HXKCORGPNW4EAGT6DALGJJ6L/graph.json","events_json":"https://pith.science/api/pith-number/57HXKCORGPNW4EAGT6DALGJJ6L/events.json","paper":"https://pith.science/paper/57HXKCOR"},"agent_actions":{"view_html":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L","download_json":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L.json","view_paper":"https://pith.science/paper/57HXKCOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.07890&json=true","fetch_graph":"https://pith.science/api/pith-number/57HXKCORGPNW4EAGT6DALGJJ6L/graph.json","fetch_events":"https://pith.science/api/pith-number/57HXKCORGPNW4EAGT6DALGJJ6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L/action/storage_attestation","attest_author":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L/action/author_attestation","sign_citation":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L/action/citation_signature","submit_replication":"https://pith.science/pith/57HXKCORGPNW4EAGT6DALGJJ6L/action/replication_record"}},"created_at":"2026-07-05T01:03:10.943442+00:00","updated_at":"2026-07-05T01:03:10.943442+00:00"}