{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O2LP5PM2N2COGYZP6KPVY5GCUQ","short_pith_number":"pith:O2LP5PM2","schema_version":"1.0","canonical_sha256":"7696febd9a6e84e3632ff29f5c74c2a43993834a5d911de96302991c3e9d690d","source":{"kind":"arxiv","id":"2108.03888","version":1},"attestation_state":"computed","paper":{"title":"Efficient Hyperparameter Optimization for Differentially Private Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Aman Priyanshu, FatemehSadat Mireshghallah, Mohammad Malekzadeh, Rakshit Naidu","submitted_at":"2021-08-09T09:18:22Z","abstract_excerpt":"Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used many times for hyperparameter search in DPSGD; e.g., via a grid search. Therefore, there is an essential need for algorithms that, within a given search space, can find near-optimal hyperparameters for the best achievable privacy-utility tradeoffs efficiently. We formulate this problem into a general optimization framework for establishing a desirable privacy-utility tradeoff, and systematically study three cost-effecti"},"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":"2108.03888","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-09T09:18:22Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"3d5062f4ae564e48b1afb4a53dc1336698352bee099c9f47d16fab5a6a60d1d3","abstract_canon_sha256":"549072df03bbd9e54af08e2c56b55ec8fa562d20e9b46e277d8a9146cca5851c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:10.657140Z","signature_b64":"xbpRKVvhMNXl+8XSyui+zV3OwbNAShnh+Qry9bD+LPUwsexH50dPwQf2YiUno8ak9Sz/CxNN1tCXKtFPmqCTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7696febd9a6e84e3632ff29f5c74c2a43993834a5d911de96302991c3e9d690d","last_reissued_at":"2026-07-05T03:04:10.656710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:10.656710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Hyperparameter Optimization for Differentially Private Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Aman Priyanshu, FatemehSadat Mireshghallah, Mohammad Malekzadeh, Rakshit Naidu","submitted_at":"2021-08-09T09:18:22Z","abstract_excerpt":"Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used many times for hyperparameter search in DPSGD; e.g., via a grid search. Therefore, there is an essential need for algorithms that, within a given search space, can find near-optimal hyperparameters for the best achievable privacy-utility tradeoffs efficiently. We formulate this problem into a general optimization framework for establishing a desirable privacy-utility tradeoff, and systematically study three cost-effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03888","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/2108.03888/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":"2108.03888","created_at":"2026-07-05T03:04:10.656776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.03888v1","created_at":"2026-07-05T03:04:10.656776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03888","created_at":"2026-07-05T03:04:10.656776+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2LP5PM2N2CO","created_at":"2026-07-05T03:04:10.656776+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2LP5PM2N2COGYZP","created_at":"2026-07-05T03:04:10.656776+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2LP5PM2","created_at":"2026-07-05T03:04:10.656776+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/O2LP5PM2N2COGYZP6KPVY5GCUQ","json":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ.json","graph_json":"https://pith.science/api/pith-number/O2LP5PM2N2COGYZP6KPVY5GCUQ/graph.json","events_json":"https://pith.science/api/pith-number/O2LP5PM2N2COGYZP6KPVY5GCUQ/events.json","paper":"https://pith.science/paper/O2LP5PM2"},"agent_actions":{"view_html":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ","download_json":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ.json","view_paper":"https://pith.science/paper/O2LP5PM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.03888&json=true","fetch_graph":"https://pith.science/api/pith-number/O2LP5PM2N2COGYZP6KPVY5GCUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/O2LP5PM2N2COGYZP6KPVY5GCUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ/action/storage_attestation","attest_author":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ/action/author_attestation","sign_citation":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ/action/citation_signature","submit_replication":"https://pith.science/pith/O2LP5PM2N2COGYZP6KPVY5GCUQ/action/replication_record"}},"created_at":"2026-07-05T03:04:10.656776+00:00","updated_at":"2026-07-05T03:04:10.656776+00:00"}