{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4TNNKGNRFPY6V2T2YM2UGQGGMO","short_pith_number":"pith:4TNNKGNR","schema_version":"1.0","canonical_sha256":"e4dad519b12bf1eaea7ac3354340c663bfa2b8e5ca187ae73732ee20e2f209e6","source":{"kind":"arxiv","id":"1908.04457","version":2},"attestation_state":"computed","paper":{"title":"On the Convergence of AdaBound and its Connection to SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pedro Savarese","submitted_at":"2019-08-13T02:00:21Z","abstract_excerpt":"Adaptive gradient methods such as Adam have gained extreme popularity due to their success in training complex neural networks and less sensitivity to hyperparameter tuning compared to SGD. However, it has been recently shown that Adam can fail to converge and might cause poor generalization -- this lead to the design of new, sophisticated adaptive methods which attempt to generalize well while being theoretically reliable. In this technical report we focus on AdaBound, a promising, recently proposed optimizer. We present a stochastic convex problem for which AdaBound can provably take arbitra"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1908.04457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T02:00:21Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ebef7a4f1a0705ce114eff2563c4bdb12ea8317376cc1ff122dd90191e0841fb","abstract_canon_sha256":"72d312e8f4f2ecb32d265c8612caf1e9166cff567b22a5e87b5d411155113081"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:55.579972Z","signature_b64":"crhlRGRJXq9LzZhGmT/polY4N0Sehe0Gr7RlrzZpStiabS4mlEF8X5AYmlrXKt3RYNoGtDoHEQqThvRUPW1uAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4dad519b12bf1eaea7ac3354340c663bfa2b8e5ca187ae73732ee20e2f209e6","last_reissued_at":"2026-07-05T00:24:55.579550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:55.579550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of AdaBound and its Connection to SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pedro Savarese","submitted_at":"2019-08-13T02:00:21Z","abstract_excerpt":"Adaptive gradient methods such as Adam have gained extreme popularity due to their success in training complex neural networks and less sensitivity to hyperparameter tuning compared to SGD. However, it has been recently shown that Adam can fail to converge and might cause poor generalization -- this lead to the design of new, sophisticated adaptive methods which attempt to generalize well while being theoretically reliable. In this technical report we focus on AdaBound, a promising, recently proposed optimizer. We present a stochastic convex problem for which AdaBound can provably take arbitra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04457","kind":"arxiv","version":2},"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/1908.04457/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.04457","created_at":"2026-07-05T00:24:55.579607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04457v2","created_at":"2026-07-05T00:24:55.579607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04457","created_at":"2026-07-05T00:24:55.579607+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TNNKGNRFPY6","created_at":"2026-07-05T00:24:55.579607+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TNNKGNRFPY6V2T2","created_at":"2026-07-05T00:24:55.579607+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TNNKGNR","created_at":"2026-07-05T00:24:55.579607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00174","citing_title":"Principled Approximation Methods for Efficient and Scalable Deep Learning","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO","json":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO.json","graph_json":"https://pith.science/api/pith-number/4TNNKGNRFPY6V2T2YM2UGQGGMO/graph.json","events_json":"https://pith.science/api/pith-number/4TNNKGNRFPY6V2T2YM2UGQGGMO/events.json","paper":"https://pith.science/paper/4TNNKGNR"},"agent_actions":{"view_html":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO","download_json":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO.json","view_paper":"https://pith.science/paper/4TNNKGNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04457&json=true","fetch_graph":"https://pith.science/api/pith-number/4TNNKGNRFPY6V2T2YM2UGQGGMO/graph.json","fetch_events":"https://pith.science/api/pith-number/4TNNKGNRFPY6V2T2YM2UGQGGMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO/action/storage_attestation","attest_author":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO/action/author_attestation","sign_citation":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO/action/citation_signature","submit_replication":"https://pith.science/pith/4TNNKGNRFPY6V2T2YM2UGQGGMO/action/replication_record"}},"created_at":"2026-07-05T00:24:55.579607+00:00","updated_at":"2026-07-05T00:24:55.579607+00:00"}