{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:R6ANBZFZRT6F2XKHKYKU4VL2YL","short_pith_number":"pith:R6ANBZFZ","canonical_record":{"source":{"id":"2006.07037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-12T09:39:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dabc026c97ee77dbaa0497499552a02e2e618943392e0b21cced539e0a5f4c2e","abstract_canon_sha256":"99f3ba8e5d2836c568298aed8ed4d0dd5f299b6b196804abcfe4a0b5ac38aa7b"},"schema_version":"1.0"},"canonical_sha256":"8f80d0e4b98cfc5d5d4756154e557ac2f55372df63972e8fcb1147710516db14","source":{"kind":"arxiv","id":"2006.07037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07037","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07037v1","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07037","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"R6ANBZFZRT6F","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"R6ANBZFZRT6F2XKH","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"R6ANBZFZ","created_at":"2026-07-05T01:09:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:R6ANBZFZRT6F2XKHKYKU4VL2YL","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-12T09:39:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dabc026c97ee77dbaa0497499552a02e2e618943392e0b21cced539e0a5f4c2e","abstract_canon_sha256":"99f3ba8e5d2836c568298aed8ed4d0dd5f299b6b196804abcfe4a0b5ac38aa7b"},"schema_version":"1.0"},"canonical_sha256":"8f80d0e4b98cfc5d5d4756154e557ac2f55372df63972e8fcb1147710516db14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:49.344385Z","signature_b64":"1UGU3aZmlcU4+ghQ8lgHMzjEPzHHOk1cykt8hmKiyGpFJFiMsKy5d0/TiorZ7xJphJj4PmjyVyVxJYbGK0AoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f80d0e4b98cfc5d5d4756154e557ac2f55372df63972e8fcb1147710516db14","last_reissued_at":"2026-07-05T01:09:49.343840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:49.343840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07037","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":"2026-07-05T01:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SlZ2zevNhYnpKsjjmJjdHi18IiHB/60zY0jtRFMP/XnsjWGDcjmJmy99zuLVhGLA2TZ1TTIDIYSkrtsjPkPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:35:30.393582Z"},"content_sha256":"778c6f3a4efcf8d8f20956be26db269d5bb4d78a5222495799518fd6dd1caace","schema_version":"1.0","event_id":"sha256:778c6f3a4efcf8d8f20956be26db269d5bb4d78a5222495799518fd6dd1caace"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:R6ANBZFZRT6F2XKHKYKU4VL2YL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Hao Zhou, Lei Li, Runxin Xu, Xunpeng Huang, Zhe Wang","submitted_at":"2020-06-12T09:39:47Z","abstract_excerpt":"Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The huge gap between theoretical convergence results and practical performances prevents further understanding of existing optimizers and the development of more advanced optimization methods. In this paper, we provide adaptive gradient methods a novel analysis with an additional mild assumption, and revise AdaGrad to \\radagrad for matching a better provable co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07037","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/2006.07037/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":"2026-07-05T01:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sWQ6lo+BJIw8JZ54CQIM+fPClGDqvQi4AGG2uaSgwcM274+7UJ9nnFInDG2S1RrLfreRND39Khx0HQyCKoVMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:35:30.394121Z"},"content_sha256":"b04dcb48d865086d8f8d387993193521674b1732cc3c8ced7a188f8dc877d92f","schema_version":"1.0","event_id":"sha256:b04dcb48d865086d8f8d387993193521674b1732cc3c8ced7a188f8dc877d92f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/bundle.json","state_url":"https://pith.science/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/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":"2026-08-03T17:35:30Z","links":{"resolver":"https://pith.science/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL","bundle":"https://pith.science/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/bundle.json","state":"https://pith.science/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6ANBZFZRT6F2XKHKYKU4VL2YL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R6ANBZFZRT6F2XKHKYKU4VL2YL","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":"99f3ba8e5d2836c568298aed8ed4d0dd5f299b6b196804abcfe4a0b5ac38aa7b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-12T09:39:47Z","title_canon_sha256":"dabc026c97ee77dbaa0497499552a02e2e618943392e0b21cced539e0a5f4c2e"},"schema_version":"1.0","source":{"id":"2006.07037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07037","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07037v1","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07037","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"R6ANBZFZRT6F","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"R6ANBZFZRT6F2XKH","created_at":"2026-07-05T01:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"R6ANBZFZ","created_at":"2026-07-05T01:09:49Z"}],"graph_snapshots":[{"event_id":"sha256:b04dcb48d865086d8f8d387993193521674b1732cc3c8ced7a188f8dc877d92f","target":"graph","created_at":"2026-07-05T01:09:49Z","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/2006.07037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The huge gap between theoretical convergence results and practical performances prevents further understanding of existing optimizers and the development of more advanced optimization methods. In this paper, we provide adaptive gradient methods a novel analysis with an additional mild assumption, and revise AdaGrad to \\radagrad for matching a better provable co","authors_text":"Hao Zhou, Lei Li, Runxin Xu, Xunpeng Huang, Zhe Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-12T09:39:47Z","title":"Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07037","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":"sha256:778c6f3a4efcf8d8f20956be26db269d5bb4d78a5222495799518fd6dd1caace","target":"record","created_at":"2026-07-05T01:09:49Z","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":"99f3ba8e5d2836c568298aed8ed4d0dd5f299b6b196804abcfe4a0b5ac38aa7b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-12T09:39:47Z","title_canon_sha256":"dabc026c97ee77dbaa0497499552a02e2e618943392e0b21cced539e0a5f4c2e"},"schema_version":"1.0","source":{"id":"2006.07037","kind":"arxiv","version":1}},"canonical_sha256":"8f80d0e4b98cfc5d5d4756154e557ac2f55372df63972e8fcb1147710516db14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f80d0e4b98cfc5d5d4756154e557ac2f55372df63972e8fcb1147710516db14","first_computed_at":"2026-07-05T01:09:49.343840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:49.343840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1UGU3aZmlcU4+ghQ8lgHMzjEPzHHOk1cykt8hmKiyGpFJFiMsKy5d0/TiorZ7xJphJj4PmjyVyVxJYbGK0AoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:49.344385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:778c6f3a4efcf8d8f20956be26db269d5bb4d78a5222495799518fd6dd1caace","sha256:b04dcb48d865086d8f8d387993193521674b1732cc3c8ced7a188f8dc877d92f"],"state_sha256":"72611b5bfe92608c8352dfcd99b094abd6ffc4c1544625e1c6119588be6c7d5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NzkBPHmCRUmFvWvtltFTMWVOYdvzsLGBQ7ERmjfbbWJXgeiHikf+XHlSeT8+YQokMcsgD1UaxH+gCfKdzw2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:35:30.397695Z","bundle_sha256":"096d5f1470ad98a94057a1b70288d31fecc5113dac121ffee6b07a8e4892a4c8"}}