{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RH672XDIC7QVDWOHB45MZBGHKP","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":"36d15ce3e54aa32d8b46b901d551f2ccaf0341f8e179dd5a3e7b1c3be85aeb1c","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:49:10Z","title_canon_sha256":"abb18bb522547cae3408a07453c7c2221da059a73cf5421ee6e99226cbf56c65"},"schema_version":"1.0","source":{"id":"2406.04443","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04443","created_at":"2026-07-05T11:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04443v3","created_at":"2026-07-05T11:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04443","created_at":"2026-07-05T11:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"RH672XDIC7QV","created_at":"2026-07-05T11:53:40Z"},{"alias_kind":"pith_short_16","alias_value":"RH672XDIC7QVDWOH","created_at":"2026-07-05T11:53:40Z"},{"alias_kind":"pith_short_8","alias_value":"RH672XDI","created_at":"2026-07-05T11:53:40Z"}],"graph_snapshots":[{"event_id":"sha256:2919e0ee283c34e0a517b35b4b250c3679c6774560e40317c46d5a4b026395b7","target":"graph","created_at":"2026-07-05T11:53:40Z","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/2406.04443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for the later ones. Gradient clipping provably helps to achieve good high-probability convergence for such noises. However, despite the similarity between AdaGrad/Adam and Clip-SGD, the current understanding of the high-probability convergence of AdaGrad/Adam-type methods is limited in this case. In this work, we prove that AdaGrad/Adam (and their delayed version) can have provably b","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Andrei Semenov, Eduard Gorbunov, Martin Tak\\'a\\v{c}, Samuel Horv\\'ath, Savelii Chezhegov, Yaroslav Klyukin","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:49:10Z","title":"Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04443","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:c5a1fd536109378bab6337654e6b865897b5cb44886875d149d5e30911634a41","target":"record","created_at":"2026-07-05T11:53:40Z","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":"36d15ce3e54aa32d8b46b901d551f2ccaf0341f8e179dd5a3e7b1c3be85aeb1c","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:49:10Z","title_canon_sha256":"abb18bb522547cae3408a07453c7c2221da059a73cf5421ee6e99226cbf56c65"},"schema_version":"1.0","source":{"id":"2406.04443","kind":"arxiv","version":3}},"canonical_sha256":"89fdfd5c6817e151d9c70f3acc84c753e54d4b0c193cf59c01871dad9ed0a940","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89fdfd5c6817e151d9c70f3acc84c753e54d4b0c193cf59c01871dad9ed0a940","first_computed_at":"2026-07-05T11:53:40.933689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:40.933689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IswWaJ8bCj6QDQTOUDMDe8Gb61Cq+3zWjLv7YgFoT6DP06chu/JoYIpIE7c9WstSSHaHB3YRJFkkU62vT1C5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:40.934181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04443","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5a1fd536109378bab6337654e6b865897b5cb44886875d149d5e30911634a41","sha256:2919e0ee283c34e0a517b35b4b250c3679c6774560e40317c46d5a4b026395b7"],"state_sha256":"e51fccbbe92c56b68281cb2ed8e1f5f7e1b797119a7011c2019ecd3f9aa26a00"}