{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QWM3OJOMNJREFZMYPPWPAQJGRA","short_pith_number":"pith:QWM3OJOM","schema_version":"1.0","canonical_sha256":"8599b725cc6a6242e5987becf0412688056d9ca3d15a194588d8ba615d7ea00c","source":{"kind":"arxiv","id":"2504.14730","version":2},"attestation_state":"computed","paper":{"title":"Optimizing Noise Distributions for Differential Privacy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Atefeh Gilani, Flavio P. Calmon, Juan Felipe Gomez, Lalitha Sankar, Oliver Kosut, Shahab Asoodeh","submitted_at":"2025-04-20T20:04:41Z","abstract_excerpt":"We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing R\\'enyi DP, a variant of DP, under a cost constraint. R\\'enyi DP has the advantage that by considering different values of the R\\'enyi parameter $\\alpha$, we can tailor our optimization for any number of compositions. To solve the optimization problem, we reduce it to a finite-dimensional convex formulation and perform preconditioned gradient descent. The resulting noise distributions are then compared to their Gaussian and Laplace counterpar"},"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":"2504.14730","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-04-20T20:04:41Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"01b44e170438b9e824f65379f8d80fb4587e8544c3a37ca1d72245535955fee9","abstract_canon_sha256":"c8f6ffc3ef61521aaf769c4d537acaa16b5b3e0992c7b18636e09ba2bddba667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:20.473413Z","signature_b64":"bhq0hZb1+kIdKHC8WuppfD21fVKSzu01FGaTnBlqCiolRiGtqKs4Z/y0KaCVMcMbL684CtcSh1x278CiC7yZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8599b725cc6a6242e5987becf0412688056d9ca3d15a194588d8ba615d7ea00c","last_reissued_at":"2026-07-05T11:18:20.472967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:20.472967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Noise Distributions for Differential Privacy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Atefeh Gilani, Flavio P. Calmon, Juan Felipe Gomez, Lalitha Sankar, Oliver Kosut, Shahab Asoodeh","submitted_at":"2025-04-20T20:04:41Z","abstract_excerpt":"We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing R\\'enyi DP, a variant of DP, under a cost constraint. R\\'enyi DP has the advantage that by considering different values of the R\\'enyi parameter $\\alpha$, we can tailor our optimization for any number of compositions. To solve the optimization problem, we reduce it to a finite-dimensional convex formulation and perform preconditioned gradient descent. The resulting noise distributions are then compared to their Gaussian and Laplace counterpar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14730","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/2504.14730/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":"2504.14730","created_at":"2026-07-05T11:18:20.473022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14730v2","created_at":"2026-07-05T11:18:20.473022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14730","created_at":"2026-07-05T11:18:20.473022+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWM3OJOMNJRE","created_at":"2026-07-05T11:18:20.473022+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWM3OJOMNJREFZMY","created_at":"2026-07-05T11:18:20.473022+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWM3OJOM","created_at":"2026-07-05T11:18:20.473022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA","json":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA.json","graph_json":"https://pith.science/api/pith-number/QWM3OJOMNJREFZMYPPWPAQJGRA/graph.json","events_json":"https://pith.science/api/pith-number/QWM3OJOMNJREFZMYPPWPAQJGRA/events.json","paper":"https://pith.science/paper/QWM3OJOM"},"agent_actions":{"view_html":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA","download_json":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA.json","view_paper":"https://pith.science/paper/QWM3OJOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14730&json=true","fetch_graph":"https://pith.science/api/pith-number/QWM3OJOMNJREFZMYPPWPAQJGRA/graph.json","fetch_events":"https://pith.science/api/pith-number/QWM3OJOMNJREFZMYPPWPAQJGRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA/action/storage_attestation","attest_author":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA/action/author_attestation","sign_citation":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA/action/citation_signature","submit_replication":"https://pith.science/pith/QWM3OJOMNJREFZMYPPWPAQJGRA/action/replication_record"}},"created_at":"2026-07-05T11:18:20.473022+00:00","updated_at":"2026-07-05T11:18:20.473022+00:00"}