{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AWJ6FXPFAROM4IRDOTEG2JJHUL","short_pith_number":"pith:AWJ6FXPF","schema_version":"1.0","canonical_sha256":"0593e2dde5045cce222374c86d2527a2d03dec2eacdb0a0c2938b65e1b2202d4","source":{"kind":"arxiv","id":"2405.12553","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ML","authors_text":"Carina Graw, Holger Dette","submitted_at":"2024-05-21T07:47:21Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is a widely used tool in machine learning. In the context of Differential Privacy (DP), SGD has been well studied in the last years in which the focus is mainly on convergence rates and privacy guarantees. While in the non private case, uncertainty quantification (UQ) for SGD by bootstrap has been addressed by several authors, these procedures cannot be transferred to differential privacy due to multiple queries to the private data. In this paper, we propose a novel block bootstrap for SGD under local differential privacy that is computationally tractable and "},"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":"2405.12553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-21T07:47:21Z","cross_cats_sorted":["cs.CR","cs.LG","math.ST","stat.CO","stat.TH"],"title_canon_sha256":"a11495faf843c8bc93642bdeb70239e48afe31b7fefa261d7ac07f82208e40be","abstract_canon_sha256":"70171376fa39edaadaa229d592e31e00daaaf9a42c0ce931f1441578b2bc2a51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:21.810365Z","signature_b64":"zIKp4dU3ehRYP9ydLEBoqXGRDSFc+3GOAT8kKnWeo25XvpGmZCUlo6/biwcdt8Sd37O/pvcxWlRJT3BCPWFIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0593e2dde5045cce222374c86d2527a2d03dec2eacdb0a0c2938b65e1b2202d4","last_reissued_at":"2026-07-05T08:21:21.809906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:21.809906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ML","authors_text":"Carina Graw, Holger Dette","submitted_at":"2024-05-21T07:47:21Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is a widely used tool in machine learning. In the context of Differential Privacy (DP), SGD has been well studied in the last years in which the focus is mainly on convergence rates and privacy guarantees. While in the non private case, uncertainty quantification (UQ) for SGD by bootstrap has been addressed by several authors, these procedures cannot be transferred to differential privacy due to multiple queries to the private data. In this paper, we propose a novel block bootstrap for SGD under local differential privacy that is computationally tractable and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12553","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/2405.12553/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":"2405.12553","created_at":"2026-07-05T08:21:21.809964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12553v1","created_at":"2026-07-05T08:21:21.809964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12553","created_at":"2026-07-05T08:21:21.809964+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWJ6FXPFAROM","created_at":"2026-07-05T08:21:21.809964+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWJ6FXPFAROM4IRD","created_at":"2026-07-05T08:21:21.809964+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWJ6FXPF","created_at":"2026-07-05T08:21:21.809964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05312","citing_title":"Locally Private Online Quantile Regression: Estimation and Inference","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL","json":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL.json","graph_json":"https://pith.science/api/pith-number/AWJ6FXPFAROM4IRDOTEG2JJHUL/graph.json","events_json":"https://pith.science/api/pith-number/AWJ6FXPFAROM4IRDOTEG2JJHUL/events.json","paper":"https://pith.science/paper/AWJ6FXPF"},"agent_actions":{"view_html":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL","download_json":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL.json","view_paper":"https://pith.science/paper/AWJ6FXPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12553&json=true","fetch_graph":"https://pith.science/api/pith-number/AWJ6FXPFAROM4IRDOTEG2JJHUL/graph.json","fetch_events":"https://pith.science/api/pith-number/AWJ6FXPFAROM4IRDOTEG2JJHUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL/action/storage_attestation","attest_author":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL/action/author_attestation","sign_citation":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL/action/citation_signature","submit_replication":"https://pith.science/pith/AWJ6FXPFAROM4IRDOTEG2JJHUL/action/replication_record"}},"created_at":"2026-07-05T08:21:21.809964+00:00","updated_at":"2026-07-05T08:21:21.809964+00:00"}