{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YPQ2E7RJ5RE2HNTBK2FVEAUSIL","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":"141f2cf56b9dd84a5a2b2c6ba322ee0053c145b7ed5a2fcec5bcdc0441a61618","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T03:45:02Z","title_canon_sha256":"4bb086b7500d093369cd825191ef6f2971369346ad3131edb0b06e6b7dc645f0"},"schema_version":"1.0","source":{"id":"2206.13033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13033","created_at":"2026-07-05T04:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13033v1","created_at":"2026-07-05T04:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13033","created_at":"2026-07-05T04:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"YPQ2E7RJ5RE2","created_at":"2026-07-05T04:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"YPQ2E7RJ5RE2HNTB","created_at":"2026-07-05T04:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"YPQ2E7RJ","created_at":"2026-07-05T04:35:01Z"}],"graph_snapshots":[{"event_id":"sha256:d560d85491cd8097039e63a783f0b33ffca166687b76c22fa4eac2edad977151","target":"graph","created_at":"2026-07-05T04:35:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.13033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data. In this paper, we study two algorithms for this purpose, i.e., DP-SGD and DP-NSGD, which first clip or normalize \\textit{per-sample} gradients to bound the sensitivity and then add noise to obfuscate the exact information. We analyze the convergence behavior of these two algorithms in the non-convex optimization setting with two common assumptions and achieve a rate $\\mathcal{O}\\left(\\sqrt[4]{\\frac{d\\log(1/\\delta)}{N^2\\epsilon^2}}\\right)$ of the ","authors_text":"Huishuai Zhang, Tie-Yan Liu, Wei Chen, Xiaodong Yang","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T03:45:02Z","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13033","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":"sha256:29bcea6da57f2cbef64ce2f8bcd4e85ad74122f86b50f592e84c72e18fb82f01","target":"record","created_at":"2026-07-05T04:35:01Z","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":"141f2cf56b9dd84a5a2b2c6ba322ee0053c145b7ed5a2fcec5bcdc0441a61618","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T03:45:02Z","title_canon_sha256":"4bb086b7500d093369cd825191ef6f2971369346ad3131edb0b06e6b7dc645f0"},"schema_version":"1.0","source":{"id":"2206.13033","kind":"arxiv","version":1}},"canonical_sha256":"c3e1a27e29ec49a3b661568b52029242fb8eb12d3b3d4ec821d4f059e01370a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e1a27e29ec49a3b661568b52029242fb8eb12d3b3d4ec821d4f059e01370a4","first_computed_at":"2026-07-05T04:35:01.831586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:01.831586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vXI7Of2N7CxD0akiDvjbeEuEZfHPU5zMDQMpz6iFKUIYKC9+v032sJuLFomRQQ0ePKGdrYNYVH8OMa2Dcu4rDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:01.832021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29bcea6da57f2cbef64ce2f8bcd4e85ad74122f86b50f592e84c72e18fb82f01","sha256:d560d85491cd8097039e63a783f0b33ffca166687b76c22fa4eac2edad977151"],"state_sha256":"4159d760dd54d22e5f85c049787d7d835c125ba349639c3c31f7329566ae2ec2"}