{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:FKIS2WP5B2V4MSF3FSKRJ6VMD3","short_pith_number":"pith:FKIS2WP5","canonical_record":{"source":{"id":"1507.02030","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-08T05:47:42Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"cfb0b2f21ce65f9982492e24cd2130a7763b41c2880a58eadeba0baa8f41e8b5","abstract_canon_sha256":"24d8e812a61cad21509e6d2e0872699fe75bc07e24ac648f52d010c12428b299"},"schema_version":"1.0"},"canonical_sha256":"2a912d59fd0eabc648bb2c9514faac1ec194624057d1b62912343678824036cd","source":{"kind":"arxiv","id":"1507.02030","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.02030","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"1507.02030v3","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.02030","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"FKIS2WP5B2V4","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FKIS2WP5B2V4MSF3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FKIS2WP5","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:FKIS2WP5B2V4MSF3FSKRJ6VMD3","target":"record","payload":{"canonical_record":{"source":{"id":"1507.02030","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-08T05:47:42Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"cfb0b2f21ce65f9982492e24cd2130a7763b41c2880a58eadeba0baa8f41e8b5","abstract_canon_sha256":"24d8e812a61cad21509e6d2e0872699fe75bc07e24ac648f52d010c12428b299"},"schema_version":"1.0"},"canonical_sha256":"2a912d59fd0eabc648bb2c9514faac1ec194624057d1b62912343678824036cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:38.169232Z","signature_b64":"MEmdc7T/cXEtPotxFM0knwmZwm1YdLRsvPHHgWYj+EF6Aez1i6OSMCooTQYDEZ4j+0sLPaFsVYtg7RQDGNWsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a912d59fd0eabc648bb2c9514faac1ec194624057d1b62912343678824036cd","last_reissued_at":"2026-05-18T01:28:38.168672Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:38.168672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.02030","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":"2026-05-18T01:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M31l4sDQNw8VxiPlNZcNz9vn0x3RwhoJGrgpj9gwC9YCjw49krjLkcpdipvYSWXSfeB9tDzUe7CljKOvC5RbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:01:23.368129Z"},"content_sha256":"2afd9e8aacb954937eeb05d9a662a506019fd38d69529abb19b5cc2a5fb5102c","schema_version":"1.0","event_id":"sha256:2afd9e8aacb954937eeb05d9a662a506019fd38d69529abb19b5cc2a5fb5102c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:FKIS2WP5B2V4MSF3FSKRJ6VMD3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Convexity: Stochastic Quasi-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Elad Hazan, Kfir Y. Levy, Shai Shalev-Shwartz","submitted_at":"2015-07-08T05:47:42Z","abstract_excerpt":"Stochastic convex optimization is a basic and well studied primitive in machine learning. It is well known that convex and Lipschitz functions can be minimized efficiently using Stochastic Gradient Descent (SGD). The Normalized Gradient Descent (NGD) algorithm, is an adaptation of Gradient Descent, which updates according to the direction of the gradients, rather than the gradients themselves. In this paper we analyze a stochastic version of NGD and prove its convergence to a global minimum for a wider class of functions: we require the functions to be quasi-convex and locally-Lipschitz. Quasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.02030","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":"2026-05-18T01:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10s3b6RC6zIViwYlkzc6VrGY9qH2V/KDFzSLek2+8TchTYf3s0uLLpjvb1nNRV4zk/Tej9s5yEcR4eJ77dRoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:01:23.368903Z"},"content_sha256":"59f3f3229fb5c77d2d25c25b96fd33eb4d517a6b8c3b1b6b12e7f9a5f4238a0b","schema_version":"1.0","event_id":"sha256:59f3f3229fb5c77d2d25c25b96fd33eb4d517a6b8c3b1b6b12e7f9a5f4238a0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/bundle.json","state_url":"https://pith.science/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/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":"2026-08-14T22:01:23Z","links":{"resolver":"https://pith.science/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3","bundle":"https://pith.science/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/bundle.json","state":"https://pith.science/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FKIS2WP5B2V4MSF3FSKRJ6VMD3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:FKIS2WP5B2V4MSF3FSKRJ6VMD3","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":"24d8e812a61cad21509e6d2e0872699fe75bc07e24ac648f52d010c12428b299","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-08T05:47:42Z","title_canon_sha256":"cfb0b2f21ce65f9982492e24cd2130a7763b41c2880a58eadeba0baa8f41e8b5"},"schema_version":"1.0","source":{"id":"1507.02030","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.02030","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"1507.02030v3","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.02030","created_at":"2026-05-18T01:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"FKIS2WP5B2V4","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FKIS2WP5B2V4MSF3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FKIS2WP5","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:59f3f3229fb5c77d2d25c25b96fd33eb4d517a6b8c3b1b6b12e7f9a5f4238a0b","target":"graph","created_at":"2026-05-18T01:28:38Z","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":"Stochastic convex optimization is a basic and well studied primitive in machine learning. It is well known that convex and Lipschitz functions can be minimized efficiently using Stochastic Gradient Descent (SGD). The Normalized Gradient Descent (NGD) algorithm, is an adaptation of Gradient Descent, which updates according to the direction of the gradients, rather than the gradients themselves. In this paper we analyze a stochastic version of NGD and prove its convergence to a global minimum for a wider class of functions: we require the functions to be quasi-convex and locally-Lipschitz. Quasi","authors_text":"Elad Hazan, Kfir Y. Levy, Shai Shalev-Shwartz","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-08T05:47:42Z","title":"Beyond Convexity: Stochastic Quasi-Convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.02030","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":"sha256:2afd9e8aacb954937eeb05d9a662a506019fd38d69529abb19b5cc2a5fb5102c","target":"record","created_at":"2026-05-18T01:28:38Z","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":"24d8e812a61cad21509e6d2e0872699fe75bc07e24ac648f52d010c12428b299","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-08T05:47:42Z","title_canon_sha256":"cfb0b2f21ce65f9982492e24cd2130a7763b41c2880a58eadeba0baa8f41e8b5"},"schema_version":"1.0","source":{"id":"1507.02030","kind":"arxiv","version":3}},"canonical_sha256":"2a912d59fd0eabc648bb2c9514faac1ec194624057d1b62912343678824036cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a912d59fd0eabc648bb2c9514faac1ec194624057d1b62912343678824036cd","first_computed_at":"2026-05-18T01:28:38.168672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:28:38.168672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MEmdc7T/cXEtPotxFM0knwmZwm1YdLRsvPHHgWYj+EF6Aez1i6OSMCooTQYDEZ4j+0sLPaFsVYtg7RQDGNWsDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:28:38.169232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.02030","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afd9e8aacb954937eeb05d9a662a506019fd38d69529abb19b5cc2a5fb5102c","sha256:59f3f3229fb5c77d2d25c25b96fd33eb4d517a6b8c3b1b6b12e7f9a5f4238a0b"],"state_sha256":"1a1d1295016f372be2c2fa6642b8a9f7ef8a472dbe97fa7cac4fb739f69fd0b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vpiA2GITVodzC5cSRM1hTtDTYi3YWpmTC8Ufwe++gNZryE7Q99D1MZLZahe/IZ6ljWr30bDDYsWj5UHwtmrqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:01:23.377966Z","bundle_sha256":"178d5c19d99d4e92a747c6fec3808264d8e7136f461017a531109c70cf38cd93"}}