{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TU7G44I5GMH4FAAQFACWQQOSEB","short_pith_number":"pith:TU7G44I5","canonical_record":{"source":{"id":"1802.05251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:20:48Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"b7d4bffab998f886647ed406af5f51777193050b24b25f0f67d7dfb694f5cc87","abstract_canon_sha256":"802de127804231325031c956c81625bb286b836a8190693e35a3ee6bd83d0ce5"},"schema_version":"1.0"},"canonical_sha256":"9d3e6e711d330fc2801028056841d22059d9d42af9649af94dd9154b6d9132de","source":{"kind":"arxiv","id":"1802.05251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05251","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05251v1","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05251","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"TU7G44I5GMH4","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TU7G44I5GMH4FAAQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TU7G44I5","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TU7G44I5GMH4FAAQFACWQQOSEB","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:20:48Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"b7d4bffab998f886647ed406af5f51777193050b24b25f0f67d7dfb694f5cc87","abstract_canon_sha256":"802de127804231325031c956c81625bb286b836a8190693e35a3ee6bd83d0ce5"},"schema_version":"1.0"},"canonical_sha256":"9d3e6e711d330fc2801028056841d22059d9d42af9649af94dd9154b6d9132de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:19.869978Z","signature_b64":"oYN9ACiDl0aY//GeBNz58Y5hjTZlQMTp89wgVimy40mTopwQs5DXQT99FvYmDp6sD/aCQgV0Vrc4tZSPVO1tDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d3e6e711d330fc2801028056841d22059d9d42af9649af94dd9154b6d9132de","last_reissued_at":"2026-05-18T00:23:19.869344Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:19.869344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05251","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh0BTqIpPuSWXJowT+J8i5PRwtGA7JOsAIJW9b4Y+RnPMcUMQwcDx4EG30hrM4uc90CGoiRH4Umr4/a89xMjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:08:28.929921Z"},"content_sha256":"ebb40bd8996e856b7d56d709555747c329441d65f7c93c2e0a8bf2848e8663d9","schema_version":"1.0","event_id":"sha256:ebb40bd8996e856b7d56d709555747c329441d65f7c93c2e0a8bf2848e8663d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TU7G44I5GMH4FAAQFACWQQOSEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentially Private Empirical Risk Minimization Revisited: Faster and More General","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Di Wang, Jinhui Xu, Minwei Ye","submitted_at":"2018-02-14T18:20:48Z","abstract_excerpt":"In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve either optimal or near optimal utility bounds with less gradient complexity compared with previous work. For ERM with smooth convex loss function in high-dimensional ($p\\gg n$) setting, we give an algorithm which achieves the upper bound with less gradient complexity than previous ones. At last, we generalize the expected excess empirical risk from convex loss fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05251","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYcPlnj5h8RtppqqimaUTY7KzVLpE53NHxT5mesRM/YyzYqdMgJwNJBL/Ujx2/m29lRhETH3TcmM83p1PZoLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:08:28.930286Z"},"content_sha256":"21346fdf6b9b8a4431e2bf2743a2eaa845c0b5aa4964575d17037f509a9a989a","schema_version":"1.0","event_id":"sha256:21346fdf6b9b8a4431e2bf2743a2eaa845c0b5aa4964575d17037f509a9a989a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TU7G44I5GMH4FAAQFACWQQOSEB/bundle.json","state_url":"https://pith.science/pith/TU7G44I5GMH4FAAQFACWQQOSEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TU7G44I5GMH4FAAQFACWQQOSEB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T17:08:28Z","links":{"resolver":"https://pith.science/pith/TU7G44I5GMH4FAAQFACWQQOSEB","bundle":"https://pith.science/pith/TU7G44I5GMH4FAAQFACWQQOSEB/bundle.json","state":"https://pith.science/pith/TU7G44I5GMH4FAAQFACWQQOSEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TU7G44I5GMH4FAAQFACWQQOSEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TU7G44I5GMH4FAAQFACWQQOSEB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"802de127804231325031c956c81625bb286b836a8190693e35a3ee6bd83d0ce5","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:20:48Z","title_canon_sha256":"b7d4bffab998f886647ed406af5f51777193050b24b25f0f67d7dfb694f5cc87"},"schema_version":"1.0","source":{"id":"1802.05251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05251","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05251v1","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05251","created_at":"2026-05-18T00:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"TU7G44I5GMH4","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TU7G44I5GMH4FAAQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TU7G44I5","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:21346fdf6b9b8a4431e2bf2743a2eaa845c0b5aa4964575d17037f509a9a989a","target":"graph","created_at":"2026-05-18T00:23:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve either optimal or near optimal utility bounds with less gradient complexity compared with previous work. For ERM with smooth convex loss function in high-dimensional ($p\\gg n$) setting, we give an algorithm which achieves the upper bound with less gradient complexity than previous ones. At last, we generalize the expected excess empirical risk from convex loss fu","authors_text":"Di Wang, Jinhui Xu, Minwei Ye","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:20:48Z","title":"Differentially Private Empirical Risk Minimization Revisited: Faster and More General"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05251","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ebb40bd8996e856b7d56d709555747c329441d65f7c93c2e0a8bf2848e8663d9","target":"record","created_at":"2026-05-18T00:23:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"802de127804231325031c956c81625bb286b836a8190693e35a3ee6bd83d0ce5","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:20:48Z","title_canon_sha256":"b7d4bffab998f886647ed406af5f51777193050b24b25f0f67d7dfb694f5cc87"},"schema_version":"1.0","source":{"id":"1802.05251","kind":"arxiv","version":1}},"canonical_sha256":"9d3e6e711d330fc2801028056841d22059d9d42af9649af94dd9154b6d9132de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3e6e711d330fc2801028056841d22059d9d42af9649af94dd9154b6d9132de","first_computed_at":"2026-05-18T00:23:19.869344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:19.869344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYN9ACiDl0aY//GeBNz58Y5hjTZlQMTp89wgVimy40mTopwQs5DXQT99FvYmDp6sD/aCQgV0Vrc4tZSPVO1tDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:19.869978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebb40bd8996e856b7d56d709555747c329441d65f7c93c2e0a8bf2848e8663d9","sha256:21346fdf6b9b8a4431e2bf2743a2eaa845c0b5aa4964575d17037f509a9a989a"],"state_sha256":"5ea80d26b7f67088f063a6de54eff9b036e9900fa3b9f6a10237cb46f743dc99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HfPdZ2vCeULAHeo7rtXXWI0oHfRRzmJ5qjNFYPE9+u1ndRxK2BExdDtB7sbXVFyg4I816M9fdj4VmWEH83C3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:08:28.932254Z","bundle_sha256":"ead3380d4a48f157673c369db0b6c32e32dad06a07264cac0e22feda2b3b0aff"}}