{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IW4JFLNESFBBB26O32EPZGPQDV","short_pith_number":"pith:IW4JFLNE","schema_version":"1.0","canonical_sha256":"45b892ada4914210ebcede88fc99f01d51733598ff8f9b50c3954ebeb76e0b7b","source":{"kind":"arxiv","id":"1908.09970","version":1},"attestation_state":"computed","paper":{"title":"Private Stochastic Convex Optimization with Optimal Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Kunal Talwar, Raef Bassily, Vitaly Feldman","submitted_at":"2019-08-27T00:50:27Z","abstract_excerpt":"We study differentially private (DP) algorithms for stochastic convex optimization (SCO). In this problem the goal is to approximately minimize the population loss given i.i.d. samples from a distribution over convex and Lipschitz loss functions. A long line of existing work on private convex optimization focuses on the empirical loss and derives asymptotically tight bounds on the excess empirical loss. However a significant gap exists in the known bounds for the population loss. We show that, up to logarithmic factors, the optimal excess population loss for DP algorithms is equal to the large"},"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":"1908.09970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-27T00:50:27Z","cross_cats_sorted":["cs.CR","cs.DS","stat.ML"],"title_canon_sha256":"3bc93a20add4b3df456c37b3e8fda118ef4e34ff50adfafba2a0c15d9a5c3cc8","abstract_canon_sha256":"4c07faf6300427f514ad91d2a5dbed41451b4074de9c66704fbc55547348906f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:52.374809Z","signature_b64":"Pqj0xCH1GTOLRc5PY22UL6Uz4Pzg09NvDFcjvos3aeuZogRXjf1SG8/raESbmMjIu5tjXZ2OG+vo8yYIxp0uCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b892ada4914210ebcede88fc99f01d51733598ff8f9b50c3954ebeb76e0b7b","last_reissued_at":"2026-07-04T23:59:52.374298Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:52.374298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private Stochastic Convex Optimization with Optimal Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Kunal Talwar, Raef Bassily, Vitaly Feldman","submitted_at":"2019-08-27T00:50:27Z","abstract_excerpt":"We study differentially private (DP) algorithms for stochastic convex optimization (SCO). In this problem the goal is to approximately minimize the population loss given i.i.d. samples from a distribution over convex and Lipschitz loss functions. A long line of existing work on private convex optimization focuses on the empirical loss and derives asymptotically tight bounds on the excess empirical loss. However a significant gap exists in the known bounds for the population loss. We show that, up to logarithmic factors, the optimal excess population loss for DP algorithms is equal to the large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09970","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/1908.09970/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":"1908.09970","created_at":"2026-07-04T23:59:52.374369+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09970v1","created_at":"2026-07-04T23:59:52.374369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09970","created_at":"2026-07-04T23:59:52.374369+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW4JFLNESFBB","created_at":"2026-07-04T23:59:52.374369+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW4JFLNESFBBB26O","created_at":"2026-07-04T23:59:52.374369+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW4JFLNE","created_at":"2026-07-04T23:59:52.374369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03294","citing_title":"A Comprehensive Guide to Differential Privacy: From Theory to User Expectations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV","json":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV.json","graph_json":"https://pith.science/api/pith-number/IW4JFLNESFBBB26O32EPZGPQDV/graph.json","events_json":"https://pith.science/api/pith-number/IW4JFLNESFBBB26O32EPZGPQDV/events.json","paper":"https://pith.science/paper/IW4JFLNE"},"agent_actions":{"view_html":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV","download_json":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV.json","view_paper":"https://pith.science/paper/IW4JFLNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09970&json=true","fetch_graph":"https://pith.science/api/pith-number/IW4JFLNESFBBB26O32EPZGPQDV/graph.json","fetch_events":"https://pith.science/api/pith-number/IW4JFLNESFBBB26O32EPZGPQDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV/action/storage_attestation","attest_author":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV/action/author_attestation","sign_citation":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV/action/citation_signature","submit_replication":"https://pith.science/pith/IW4JFLNESFBBB26O32EPZGPQDV/action/replication_record"}},"created_at":"2026-07-04T23:59:52.374369+00:00","updated_at":"2026-07-04T23:59:52.374369+00:00"}