{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YPQ2E7RJ5RE2HNTBK2FVEAUSIL","short_pith_number":"pith:YPQ2E7RJ","canonical_record":{"source":{"id":"2206.13033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T03:45:02Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"4bb086b7500d093369cd825191ef6f2971369346ad3131edb0b06e6b7dc645f0","abstract_canon_sha256":"141f2cf56b9dd84a5a2b2c6ba322ee0053c145b7ed5a2fcec5bcdc0441a61618"},"schema_version":"1.0"},"canonical_sha256":"c3e1a27e29ec49a3b661568b52029242fb8eb12d3b3d4ec821d4f059e01370a4","source":{"kind":"arxiv","id":"2206.13033","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YPQ2E7RJ5RE2HNTBK2FVEAUSIL","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T03:45:02Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"4bb086b7500d093369cd825191ef6f2971369346ad3131edb0b06e6b7dc645f0","abstract_canon_sha256":"141f2cf56b9dd84a5a2b2c6ba322ee0053c145b7ed5a2fcec5bcdc0441a61618"},"schema_version":"1.0"},"canonical_sha256":"c3e1a27e29ec49a3b661568b52029242fb8eb12d3b3d4ec821d4f059e01370a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:01.832021Z","signature_b64":"vXI7Of2N7CxD0akiDvjbeEuEZfHPU5zMDQMpz6iFKUIYKC9+v032sJuLFomRQQ0ePKGdrYNYVH8OMa2Dcu4rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e1a27e29ec49a3b661568b52029242fb8eb12d3b3d4ec821d4f059e01370a4","last_reissued_at":"2026-07-05T04:35:01.831586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:01.831586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13033","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":"2026-07-05T04:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KcNu3T3ZPcboWqfDurh36NDPrr4sRiVomX0cSgsLTdw7j8gTpILX/TkyWddH8mPiP0n/aTeLXZIPeH7nmVjKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:44:07.723611Z"},"content_sha256":"29bcea6da57f2cbef64ce2f8bcd4e85ad74122f86b50f592e84c72e18fb82f01","schema_version":"1.0","event_id":"sha256:29bcea6da57f2cbef64ce2f8bcd4e85ad74122f86b50f592e84c72e18fb82f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YPQ2E7RJ5RE2HNTBK2FVEAUSIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Tie-Yan Liu, Wei Chen, Xiaodong Yang","submitted_at":"2022-06-27T03:45:02Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13033","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/2206.13033/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73KM53cD/zAULR4v63FHjt2/bU6XApHqGftl0/24jBrndlncpxx3BjOcxV+xfWyX8DkSll1OwT13epWM48RaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:44:07.724140Z"},"content_sha256":"d560d85491cd8097039e63a783f0b33ffca166687b76c22fa4eac2edad977151","schema_version":"1.0","event_id":"sha256:d560d85491cd8097039e63a783f0b33ffca166687b76c22fa4eac2edad977151"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/bundle.json","state_url":"https://pith.science/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/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":"2026-08-05T11:44:07Z","links":{"resolver":"https://pith.science/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL","bundle":"https://pith.science/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/bundle.json","state":"https://pith.science/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPQ2E7RJ5RE2HNTBK2FVEAUSIL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhuMebPufd5XjuxQ2DWlcLnu+ZknuWrjlt2QYWozHBavBfYfeym0lp0yIrDFZaiw6ELHMrHbig1+gBEA7Q47Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:44:07.730989Z","bundle_sha256":"07d46b48dedf1c2e6345c44e280b2ed2aa0fe5a1883f18d6e4ca20ea1390ca1b"}}