{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76N4DHRHE57HXQHKBHEGDIH2SC","short_pith_number":"pith:76N4DHRH","schema_version":"1.0","canonical_sha256":"ff9bc19e27277e7bc0ea09c861a0fa908bdcdbae66b1bd422ee24419cb7b4454","source":{"kind":"arxiv","id":"2406.02716","version":2},"attestation_state":"computed","paper":{"title":"Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Arun Ganesh, Christopher A. Choquette-Choo","submitted_at":"2024-06-04T18:59:42Z","abstract_excerpt":"In this paper we revisit the DP stochastic convex optimization (SCO) problem. For convex smooth losses, it is well-known that the canonical DP-SGD (stochastic gradient descent) achieves the optimal rate of $O\\left(\\frac{LR}{\\sqrt{n}} + \\frac{LR \\sqrt{p \\log(1/\\delta)}}{\\epsilon n}\\right)$ under $(\\epsilon, \\delta)$-DP, and also well-known that variants of DP-SGD can achieve the optimal rate in a single epoch. However, the batch gradient complexity (i.e., number of adaptive optimization steps), which is important in applications like federated learning, is less well-understood. In particular, a"},"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":"2406.02716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T18:59:42Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"3354a54729f21342e5f0c86d308c7f60b9ffe92ed31a38e9ddf21fb375c04bb0","abstract_canon_sha256":"88bfba69a5489ae779ac820267b252942a9e8760434edeb3311afe26786cbf65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:54.394860Z","signature_b64":"LZANcN7+V6FO5MgJz/bSZd40c3jilTU/AiIlyu3coh47+LNHqhXSVxIVEEUvdBiTqtAqnfLKYoX2pSRoJwOeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9bc19e27277e7bc0ea09c861a0fa908bdcdbae66b1bd422ee24419cb7b4454","last_reissued_at":"2026-07-05T09:14:54.394425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:54.394425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Arun Ganesh, Christopher A. Choquette-Choo","submitted_at":"2024-06-04T18:59:42Z","abstract_excerpt":"In this paper we revisit the DP stochastic convex optimization (SCO) problem. For convex smooth losses, it is well-known that the canonical DP-SGD (stochastic gradient descent) achieves the optimal rate of $O\\left(\\frac{LR}{\\sqrt{n}} + \\frac{LR \\sqrt{p \\log(1/\\delta)}}{\\epsilon n}\\right)$ under $(\\epsilon, \\delta)$-DP, and also well-known that variants of DP-SGD can achieve the optimal rate in a single epoch. However, the batch gradient complexity (i.e., number of adaptive optimization steps), which is important in applications like federated learning, is less well-understood. In particular, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02716","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.02716/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":"2406.02716","created_at":"2026-07-05T09:14:54.394482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02716v2","created_at":"2026-07-05T09:14:54.394482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02716","created_at":"2026-07-05T09:14:54.394482+00:00"},{"alias_kind":"pith_short_12","alias_value":"76N4DHRHE57H","created_at":"2026-07-05T09:14:54.394482+00:00"},{"alias_kind":"pith_short_16","alias_value":"76N4DHRHE57HXQHK","created_at":"2026-07-05T09:14:54.394482+00:00"},{"alias_kind":"pith_short_8","alias_value":"76N4DHRH","created_at":"2026-07-05T09:14:54.394482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08201","citing_title":"Correlated Noise Mechanisms for Differentially Private Learning","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC","json":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC.json","graph_json":"https://pith.science/api/pith-number/76N4DHRHE57HXQHKBHEGDIH2SC/graph.json","events_json":"https://pith.science/api/pith-number/76N4DHRHE57HXQHKBHEGDIH2SC/events.json","paper":"https://pith.science/paper/76N4DHRH"},"agent_actions":{"view_html":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC","download_json":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC.json","view_paper":"https://pith.science/paper/76N4DHRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02716&json=true","fetch_graph":"https://pith.science/api/pith-number/76N4DHRHE57HXQHKBHEGDIH2SC/graph.json","fetch_events":"https://pith.science/api/pith-number/76N4DHRHE57HXQHKBHEGDIH2SC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC/action/storage_attestation","attest_author":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC/action/author_attestation","sign_citation":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC/action/citation_signature","submit_replication":"https://pith.science/pith/76N4DHRHE57HXQHKBHEGDIH2SC/action/replication_record"}},"created_at":"2026-07-05T09:14:54.394482+00:00","updated_at":"2026-07-05T09:14:54.394482+00:00"}