{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:C3MXMELCNLFJ3GES6Q6TBYQIGM","short_pith_number":"pith:C3MXMELC","schema_version":"1.0","canonical_sha256":"16d97611626aca9d9892f43d30e2083338b6a2a4bc7d32f51f77b8506dbb71a6","source":{"kind":"arxiv","id":"1405.7085","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Adam Smith, Raef Bassily","submitted_at":"2014-05-27T22:58:26Z","abstract_excerpt":"In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower bounds for private ERM assuming only that each data point's contribution to the loss function is Lipschitz bounded and that the domain of optimization is bounded. We provide a separate set of algorithms and matching lower bounds for the setting in which the loss functions are known to also be strongly convex.\n  Our algorithms run in polynomial time, and in "},"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":"1405.7085","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-27T22:58:26Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"41d401f2fc13c126f3615967a5054e8f56318239a42653aab0ea10e1a8faf309","abstract_canon_sha256":"c3848879ede652443ac9cb4e58a0b19b0f46530e0b7825a3267c8bb152e58bb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:48.164459Z","signature_b64":"FMZn/rIwZIMdhKoxmXsXpcJfHtqXR5QDWqK9TnxYmYEA684gId6dhsSa1QJBC/xPWAhobNIUw2h3qryA74SzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d97611626aca9d9892f43d30e2083338b6a2a4bc7d32f51f77b8506dbb71a6","last_reissued_at":"2026-05-18T02:39:48.163801Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:48.163801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Adam Smith, Raef Bassily","submitted_at":"2014-05-27T22:58:26Z","abstract_excerpt":"In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower bounds for private ERM assuming only that each data point's contribution to the loss function is Lipschitz bounded and that the domain of optimization is bounded. We provide a separate set of algorithms and matching lower bounds for the setting in which the loss functions are known to also be strongly convex.\n  Our algorithms run in polynomial time, and in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.7085","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":"1405.7085","created_at":"2026-05-18T02:39:48.163905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.7085v2","created_at":"2026-05-18T02:39:48.163905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.7085","created_at":"2026-05-18T02:39:48.163905+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3MXMELCNLFJ","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3MXMELCNLFJ3GES","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3MXMELC","created_at":"2026-05-18T12:28:22.404517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2505.05707","citing_title":"Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19813","citing_title":"General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16334","citing_title":"Preventing overfitting in deep learning using differential privacy","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM","json":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM.json","graph_json":"https://pith.science/api/pith-number/C3MXMELCNLFJ3GES6Q6TBYQIGM/graph.json","events_json":"https://pith.science/api/pith-number/C3MXMELCNLFJ3GES6Q6TBYQIGM/events.json","paper":"https://pith.science/paper/C3MXMELC"},"agent_actions":{"view_html":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM","download_json":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM.json","view_paper":"https://pith.science/paper/C3MXMELC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.7085&json=true","fetch_graph":"https://pith.science/api/pith-number/C3MXMELCNLFJ3GES6Q6TBYQIGM/graph.json","fetch_events":"https://pith.science/api/pith-number/C3MXMELCNLFJ3GES6Q6TBYQIGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM/action/storage_attestation","attest_author":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM/action/author_attestation","sign_citation":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM/action/citation_signature","submit_replication":"https://pith.science/pith/C3MXMELCNLFJ3GES6Q6TBYQIGM/action/replication_record"}},"created_at":"2026-05-18T02:39:48.163905+00:00","updated_at":"2026-05-18T02:39:48.163905+00:00"}