{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6MRZK63XVDSJ27V65W4Q3KVQ2K","short_pith_number":"pith:6MRZK63X","canonical_record":{"source":{"id":"1810.00553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-01T07:07:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"83768a133c8284f2f88ce46dfcacbc4b0ec934cacbbdcc512999af65924409fd","abstract_canon_sha256":"1948e28e856309ad1fa303a473d660acb3421d6d474a9aca2696b0f52c5e2db7"},"schema_version":"1.0"},"canonical_sha256":"f323957b77a8e49d7ebeedb90daab0d2badd9f1f5924add0292b61d2322e5ff3","source":{"kind":"arxiv","id":"1810.00553","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00553","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00553v1","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00553","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"6MRZK63XVDSJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6MRZK63XVDSJ27V6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6MRZK63X","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6MRZK63XVDSJ27V65W4Q3KVQ2K","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-01T07:07:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"83768a133c8284f2f88ce46dfcacbc4b0ec934cacbbdcc512999af65924409fd","abstract_canon_sha256":"1948e28e856309ad1fa303a473d660acb3421d6d474a9aca2696b0f52c5e2db7"},"schema_version":"1.0"},"canonical_sha256":"f323957b77a8e49d7ebeedb90daab0d2badd9f1f5924add0292b61d2322e5ff3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:25.433906Z","signature_b64":"+72szNjhRsNxiskkRZFR2K+AL0tYuDoju4TP0+vtTfutCSDsxOLD8DPC933+YN0jH03yQbkoSR0LqYYXaW6+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f323957b77a8e49d7ebeedb90daab0d2badd9f1f5924add0292b61d2322e5ff3","last_reissued_at":"2026-05-18T00:04:25.433248Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:25.433248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00553","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":"2026-05-18T00:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WM6gF27Y9lpSMnqvNCWN9iTE9a6KJq8a6AXQOw7zf1bTKP3Qe/8CG35EGIZK/LmPLEpe8ahHFOghIhYtto4yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:13:00.734654Z"},"content_sha256":"08539ad86e52c59bf7264e5ba92a5d1bc91cb6f1ea2c075f24fd30899ee5b685","schema_version":"1.0","event_id":"sha256:08539ad86e52c59bf7264e5ba92a5d1bc91cb6f1ea2c075f24fd30899ee5b685"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6MRZK63XVDSJ27V65W4Q3KVQ2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Adaptive and Accelerated Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guanghui Lan, Qi Deng, Yi Cheng","submitted_at":"2018-10-01T07:07:47Z","abstract_excerpt":"Stochastic gradient descent (\\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive gradient) methods are the two main techniques to improve the slow convergence of \\textsc{Sgd}. While empirical studies have demonstrated potential advantages of combining these two techniques, it remains unknown whether these methods can achieve the optimal rate of convergence for stochastic optimization. In this paper, we present a new class of adaptive and accel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00553","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":""},"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":"2026-05-18T00:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnyIfoVUjmJKTqkcJjUoF71NURkLZVFCxyFy1Y9uRi3OacL2oVCkOhXiz0r7xCpNYzxm4ACjjx7pzFqQ100yAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:13:00.735342Z"},"content_sha256":"c4ca6beda0b1667901d9f17003428f912ec842350c81ac5501896c8ba26cfe45","schema_version":"1.0","event_id":"sha256:c4ca6beda0b1667901d9f17003428f912ec842350c81ac5501896c8ba26cfe45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/bundle.json","state_url":"https://pith.science/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/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":"2026-06-10T05:13:00Z","links":{"resolver":"https://pith.science/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K","bundle":"https://pith.science/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/bundle.json","state":"https://pith.science/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MRZK63XVDSJ27V65W4Q3KVQ2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6MRZK63XVDSJ27V65W4Q3KVQ2K","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":"1948e28e856309ad1fa303a473d660acb3421d6d474a9aca2696b0f52c5e2db7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-01T07:07:47Z","title_canon_sha256":"83768a133c8284f2f88ce46dfcacbc4b0ec934cacbbdcc512999af65924409fd"},"schema_version":"1.0","source":{"id":"1810.00553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00553","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00553v1","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00553","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"6MRZK63XVDSJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6MRZK63XVDSJ27V6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6MRZK63X","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:c4ca6beda0b1667901d9f17003428f912ec842350c81ac5501896c8ba26cfe45","target":"graph","created_at":"2026-05-18T00:04:25Z","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 gradient descent (\\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive gradient) methods are the two main techniques to improve the slow convergence of \\textsc{Sgd}. While empirical studies have demonstrated potential advantages of combining these two techniques, it remains unknown whether these methods can achieve the optimal rate of convergence for stochastic optimization. In this paper, we present a new class of adaptive and accel","authors_text":"Guanghui Lan, Qi Deng, Yi Cheng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-01T07:07:47Z","title":"Optimal Adaptive and Accelerated Stochastic Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00553","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":"sha256:08539ad86e52c59bf7264e5ba92a5d1bc91cb6f1ea2c075f24fd30899ee5b685","target":"record","created_at":"2026-05-18T00:04:25Z","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":"1948e28e856309ad1fa303a473d660acb3421d6d474a9aca2696b0f52c5e2db7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-01T07:07:47Z","title_canon_sha256":"83768a133c8284f2f88ce46dfcacbc4b0ec934cacbbdcc512999af65924409fd"},"schema_version":"1.0","source":{"id":"1810.00553","kind":"arxiv","version":1}},"canonical_sha256":"f323957b77a8e49d7ebeedb90daab0d2badd9f1f5924add0292b61d2322e5ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f323957b77a8e49d7ebeedb90daab0d2badd9f1f5924add0292b61d2322e5ff3","first_computed_at":"2026-05-18T00:04:25.433248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:25.433248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+72szNjhRsNxiskkRZFR2K+AL0tYuDoju4TP0+vtTfutCSDsxOLD8DPC933+YN0jH03yQbkoSR0LqYYXaW6+BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:25.433906Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08539ad86e52c59bf7264e5ba92a5d1bc91cb6f1ea2c075f24fd30899ee5b685","sha256:c4ca6beda0b1667901d9f17003428f912ec842350c81ac5501896c8ba26cfe45"],"state_sha256":"0957c154fdd5ca75f0e4e32fc1373eecc1beaeacd5bea80770bdf4a6c725b0e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpn/KI94XzfnWYQ0brBIaCLrIk5f25PXIpemt/Lv2sM6BQjz9z+L6Tzqq9v+U/+DeczwSqh9dL5ZKd24smM/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T05:13:00.741085Z","bundle_sha256":"ff71c9cb4943f62bfcc30c7314076bd29476a162ab181441197753d676f7a1fe"}}