{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:URRFKIICWKSB5GBGRXG4N6GXAQ","short_pith_number":"pith:URRFKIIC","canonical_record":{"source":{"id":"2409.09745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T14:20:03Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a0595ed3a14b4e6f952f7cab83986747a0353ccd2776a3167f5204db3f763076","abstract_canon_sha256":"69051820b1ea6b77b4cd69cbd807b0a0696c10739b10f2ea5210aa9fd738684a"},"schema_version":"1.0"},"canonical_sha256":"a462552102b2a41e98268dcdc6f8d7040c6a869dae0e3456773f4d6c88811554","source":{"kind":"arxiv","id":"2409.09745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09745","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09745v1","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09745","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"URRFKIICWKSB","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"URRFKIICWKSB5GBG","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"URRFKIIC","created_at":"2026-07-05T09:07:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:URRFKIICWKSB5GBGRXG4N6GXAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T14:20:03Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a0595ed3a14b4e6f952f7cab83986747a0353ccd2776a3167f5204db3f763076","abstract_canon_sha256":"69051820b1ea6b77b4cd69cbd807b0a0696c10739b10f2ea5210aa9fd738684a"},"schema_version":"1.0"},"canonical_sha256":"a462552102b2a41e98268dcdc6f8d7040c6a869dae0e3456773f4d6c88811554","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:13.958598Z","signature_b64":"LUCU1h6UQOKcpiOEk2ks1aXW0yFeaOU0VelPA7T/RyBdHmTnwVyc/d23enlIDZgWmoYYP8bweZxQwAwxBVcECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a462552102b2a41e98268dcdc6f8d7040c6a869dae0e3456773f4d6c88811554","last_reissued_at":"2026-07-05T09:07:13.958100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:13.958100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09745","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":"2026-07-05T09:07:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GQMIpiER/Gx2bj25EQd68BwmcrMzxfWuircOtrYtisSzgTC9LrTTsqbAVMjQKlqv1XldaTAVnUxx65RrgxmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:33:26.389239Z"},"content_sha256":"1f706d7e87b725b17462fce5a910233d22fe7aea26724cc9a20069b109f3abea","schema_version":"1.0","event_id":"sha256:1f706d7e87b725b17462fce5a910233d22fe7aea26724cc9a20069b109f3abea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:URRFKIICWKSB5GBGRXG4N6GXAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Cong Fang, Haihan Zhang, Qianwen Chen, Yuanshi Liu","submitted_at":"2024-09-15T14:20:03Z","abstract_excerpt":"Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. However, a fundamental question -- for what kinds of high-dimensional learning problems SGD and its accelerated variants can achieve optimality has yet to be well studied. This paper investigates SGD with two essential components in practice: exponentially decaying step size schedule and momentum. We establish the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09745","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/2409.09745/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":"2026-07-05T09:07:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKZOZ9yYHL6Z4P61w6gzIzpP7efKugxbc0cD1wk4QAGTDDCn0YGD4lpbA2GPZHOTSC1phHQqzkJlFBBzlECHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:33:26.389747Z"},"content_sha256":"6c5bac35bda42ea3dea443f9021d455dac303c561a06eaffd66122959fdf5de5","schema_version":"1.0","event_id":"sha256:6c5bac35bda42ea3dea443f9021d455dac303c561a06eaffd66122959fdf5de5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/bundle.json","state_url":"https://pith.science/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/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":"2026-08-17T03:33:26Z","links":{"resolver":"https://pith.science/pith/URRFKIICWKSB5GBGRXG4N6GXAQ","bundle":"https://pith.science/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/bundle.json","state":"https://pith.science/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URRFKIICWKSB5GBGRXG4N6GXAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:URRFKIICWKSB5GBGRXG4N6GXAQ","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":"69051820b1ea6b77b4cd69cbd807b0a0696c10739b10f2ea5210aa9fd738684a","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T14:20:03Z","title_canon_sha256":"a0595ed3a14b4e6f952f7cab83986747a0353ccd2776a3167f5204db3f763076"},"schema_version":"1.0","source":{"id":"2409.09745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09745","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09745v1","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09745","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"URRFKIICWKSB","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"URRFKIICWKSB5GBG","created_at":"2026-07-05T09:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"URRFKIIC","created_at":"2026-07-05T09:07:13Z"}],"graph_snapshots":[{"event_id":"sha256:6c5bac35bda42ea3dea443f9021d455dac303c561a06eaffd66122959fdf5de5","target":"graph","created_at":"2026-07-05T09:07:13Z","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/2409.09745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. However, a fundamental question -- for what kinds of high-dimensional learning problems SGD and its accelerated variants can achieve optimality has yet to be well studied. This paper investigates SGD with two essential components in practice: exponentially decaying step size schedule and momentum. We establish the co","authors_text":"Cong Fang, Haihan Zhang, Qianwen Chen, Yuanshi Liu","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T14:20:03Z","title":"The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09745","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":"sha256:1f706d7e87b725b17462fce5a910233d22fe7aea26724cc9a20069b109f3abea","target":"record","created_at":"2026-07-05T09:07:13Z","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":"69051820b1ea6b77b4cd69cbd807b0a0696c10739b10f2ea5210aa9fd738684a","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T14:20:03Z","title_canon_sha256":"a0595ed3a14b4e6f952f7cab83986747a0353ccd2776a3167f5204db3f763076"},"schema_version":"1.0","source":{"id":"2409.09745","kind":"arxiv","version":1}},"canonical_sha256":"a462552102b2a41e98268dcdc6f8d7040c6a869dae0e3456773f4d6c88811554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a462552102b2a41e98268dcdc6f8d7040c6a869dae0e3456773f4d6c88811554","first_computed_at":"2026-07-05T09:07:13.958100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:13.958100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LUCU1h6UQOKcpiOEk2ks1aXW0yFeaOU0VelPA7T/RyBdHmTnwVyc/d23enlIDZgWmoYYP8bweZxQwAwxBVcECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:13.958598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f706d7e87b725b17462fce5a910233d22fe7aea26724cc9a20069b109f3abea","sha256:6c5bac35bda42ea3dea443f9021d455dac303c561a06eaffd66122959fdf5de5"],"state_sha256":"faa263c7a3c578a3f22cc685c9a044b67ccb9d8d6a65e5f879ccd3bb991ffe70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vNvxGvVpgzVKT9zW7CyIjety5cang/ftQxu41KbU948mlh5glcI4Caa3CsIPHvhv5gSOE86ZpHBoVrvbGXVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:33:26.394724Z","bundle_sha256":"03f6ea009eb6ec733172a1f163d56512564811f0869563b1f1c9b284425e50b7"}}