{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XOIJSSPFOZDIKLC3XPUQVK66TM","short_pith_number":"pith:XOIJSSPF","canonical_record":{"source":{"id":"1802.06903","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T23:04:20Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"eb3efef9c27c4c104b2f6f466f1b3b84970dbc203427c71be6063533478edf72","abstract_canon_sha256":"40ec8a240c96196c4d0dba5179f51d699491c3d94c73faa8e25dfe3037a0411c"},"schema_version":"1.0"},"canonical_sha256":"bb909949e57646852c5bbbe90aabde9b31d1cca5cfcafabd51871971f3f8ece0","source":{"kind":"arxiv","id":"1802.06903","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06903","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06903v3","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06903","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"XOIJSSPFOZDI","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOIJSSPFOZDIKLC3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOIJSSPF","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XOIJSSPFOZDIKLC3XPUQVK66TM","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06903","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T23:04:20Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"eb3efef9c27c4c104b2f6f466f1b3b84970dbc203427c71be6063533478edf72","abstract_canon_sha256":"40ec8a240c96196c4d0dba5179f51d699491c3d94c73faa8e25dfe3037a0411c"},"schema_version":"1.0"},"canonical_sha256":"bb909949e57646852c5bbbe90aabde9b31d1cca5cfcafabd51871971f3f8ece0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.744996Z","signature_b64":"yYf7/I5y2XOLxVO86XXSFw0uTw0euIZW6cOCP+ZXPtHYqOP6CvASQmrmACk4hstbV+mvKGB8x8kRNoX7eTpkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb909949e57646852c5bbbe90aabde9b31d1cca5cfcafabd51871971f3f8ece0","last_reissued_at":"2026-05-17T23:51:54.744498Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.744498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06903","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZvrlkegQXHI69EB3zqyBdM7QkZNrUVCOJiK/AuQVmeblsr7Af0LyT48MbfC0+VSic/wmz6+646mjCmVfRP7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:07:40.027830Z"},"content_sha256":"73efa281c7a39dc2eaa894945c18fbac08bbd709ed8a38f61de922899d4f3117","schema_version":"1.0","event_id":"sha256:73efa281c7a39dc2eaa894945c18fbac08bbd709ed8a38f61de922899d4f3117"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XOIJSSPFOZDIKLC3XPUQVK66TM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Huishuai Zhang, Yingbin Liang, Yi Zhou","submitted_at":"2018-02-19T23:04:20Z","abstract_excerpt":"The success of deep learning has led to a rising interest in the generalization property of the stochastic gradient descent (SGD) method, and stability is one popular approach to study it. Existing works based on stability have studied nonconvex loss functions, but only considered the generalization error of the SGD in expectation. In this paper, we establish various generalization error bounds with probabilistic guarantee for the SGD. Specifically, for both general nonconvex loss functions and gradient dominant loss functions, we characterize the on-average stability of the iterates generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06903","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kj89RBkZF8RXEkyXiEAmxOU382Q4Jt6tikU7VxaaftfzdAPuPnQrleOPKpY5bePvLAfVSfnj61J7GVBYEUqNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:07:40.028515Z"},"content_sha256":"150e5152b14575d68b0a6dd1b0fb50b0e3597dcf4492737886d62fd8a48e1046","schema_version":"1.0","event_id":"sha256:150e5152b14575d68b0a6dd1b0fb50b0e3597dcf4492737886d62fd8a48e1046"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/bundle.json","state_url":"https://pith.science/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/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":"2026-05-26T09:07:40Z","links":{"resolver":"https://pith.science/pith/XOIJSSPFOZDIKLC3XPUQVK66TM","bundle":"https://pith.science/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/bundle.json","state":"https://pith.science/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOIJSSPFOZDIKLC3XPUQVK66TM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XOIJSSPFOZDIKLC3XPUQVK66TM","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":"40ec8a240c96196c4d0dba5179f51d699491c3d94c73faa8e25dfe3037a0411c","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T23:04:20Z","title_canon_sha256":"eb3efef9c27c4c104b2f6f466f1b3b84970dbc203427c71be6063533478edf72"},"schema_version":"1.0","source":{"id":"1802.06903","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06903","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06903v3","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06903","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"XOIJSSPFOZDI","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOIJSSPFOZDIKLC3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOIJSSPF","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:150e5152b14575d68b0a6dd1b0fb50b0e3597dcf4492737886d62fd8a48e1046","target":"graph","created_at":"2026-05-17T23:51:54Z","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"},"paper":{"abstract_excerpt":"The success of deep learning has led to a rising interest in the generalization property of the stochastic gradient descent (SGD) method, and stability is one popular approach to study it. Existing works based on stability have studied nonconvex loss functions, but only considered the generalization error of the SGD in expectation. In this paper, we establish various generalization error bounds with probabilistic guarantee for the SGD. Specifically, for both general nonconvex loss functions and gradient dominant loss functions, we characterize the on-average stability of the iterates generated","authors_text":"Huishuai Zhang, Yingbin Liang, Yi Zhou","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T23:04:20Z","title":"Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06903","kind":"arxiv","version":3},"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":"sha256:73efa281c7a39dc2eaa894945c18fbac08bbd709ed8a38f61de922899d4f3117","target":"record","created_at":"2026-05-17T23:51:54Z","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":"40ec8a240c96196c4d0dba5179f51d699491c3d94c73faa8e25dfe3037a0411c","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T23:04:20Z","title_canon_sha256":"eb3efef9c27c4c104b2f6f466f1b3b84970dbc203427c71be6063533478edf72"},"schema_version":"1.0","source":{"id":"1802.06903","kind":"arxiv","version":3}},"canonical_sha256":"bb909949e57646852c5bbbe90aabde9b31d1cca5cfcafabd51871971f3f8ece0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb909949e57646852c5bbbe90aabde9b31d1cca5cfcafabd51871971f3f8ece0","first_computed_at":"2026-05-17T23:51:54.744498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:54.744498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYf7/I5y2XOLxVO86XXSFw0uTw0euIZW6cOCP+ZXPtHYqOP6CvASQmrmACk4hstbV+mvKGB8x8kRNoX7eTpkCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:54.744996Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06903","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73efa281c7a39dc2eaa894945c18fbac08bbd709ed8a38f61de922899d4f3117","sha256:150e5152b14575d68b0a6dd1b0fb50b0e3597dcf4492737886d62fd8a48e1046"],"state_sha256":"e2c555c23814e5a10a1daa30e7024a4dbac4ec969ea42301b9f4aa054b94b15e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gk28bA6Y8sKnPVvhoHVpiXs7vrEnqy/SZ1BdruUfE0lKfWJfVlIe4lAdcJymvrzK9AvcFU8oQ+ZNwCvu4PnjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T09:07:40.032278Z","bundle_sha256":"ebd873cfab79b82ed9d134d7712767c661a2d6980f3c93c4e8ff3ee7e842729d"}}