{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KTBF2AKOPGOD7GATG65VFNYA3G","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":"9417a84c8f867a32235e37b8deb5273c4a0a678e82c577e1d2aa6b8421d5e30e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T21:00:55Z","title_canon_sha256":"b427ab0616a130d876a71de18d07a540eec46d7ed56d5ae07cab2d9006ea8c8c"},"schema_version":"1.0","source":{"id":"2202.00089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00089","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00089v1","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00089","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"KTBF2AKOPGOD","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"KTBF2AKOPGOD7GAT","created_at":"2026-07-05T03:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"KTBF2AKO","created_at":"2026-07-05T03:53:18Z"}],"graph_snapshots":[{"event_id":"sha256:289d576251e4ed0fb1edd5a7d64f7256c9c3cd705be5cc834bac8efeadd796e3","target":"graph","created_at":"2026-07-05T03:53:18Z","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/2202.00089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adam has been widely adopted for training deep neural networks due to less hyperparameter tuning and remarkable performance. To improve generalization, Adam is typically used in tandem with a squared $\\ell_2$ regularizer (referred to as Adam-$\\ell_2$). However, even better performance can be obtained with AdamW, which decouples the gradient of the regularizer from the update rule of Adam-$\\ell_2$. Yet, we are still lacking a complete explanation of the advantages of AdamW. In this paper, we tackle this question from both an optimization and an empirical point of view. First, we show how to re-","authors_text":"Ashok Cutkosky, Francesco Orabona, Mingrui Liu, Zhenxun Zhuang","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T21:00:55Z","title":"Understanding AdamW through Proximal Methods and Scale-Freeness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00089","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:f868f5eca6be50d0cc470f13f4996197bc739e074bce6f14a41ed50b00cc0d5f","target":"record","created_at":"2026-07-05T03:53:18Z","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":"9417a84c8f867a32235e37b8deb5273c4a0a678e82c577e1d2aa6b8421d5e30e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T21:00:55Z","title_canon_sha256":"b427ab0616a130d876a71de18d07a540eec46d7ed56d5ae07cab2d9006ea8c8c"},"schema_version":"1.0","source":{"id":"2202.00089","kind":"arxiv","version":1}},"canonical_sha256":"54c25d014e799c3f981337bb52b700d98a103dc223e24412ce259eec938605da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54c25d014e799c3f981337bb52b700d98a103dc223e24412ce259eec938605da","first_computed_at":"2026-07-05T03:53:18.459616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:18.459616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r1QguVdIAPgjateiJerKgoyyQw5kyFJ0l9FHpTPMZ0VwAx8FpRq2anV7xuw8pDlf7wA4EUL4XDbSOZIRqGeXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:18.460049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f868f5eca6be50d0cc470f13f4996197bc739e074bce6f14a41ed50b00cc0d5f","sha256:289d576251e4ed0fb1edd5a7d64f7256c9c3cd705be5cc834bac8efeadd796e3"],"state_sha256":"fa031ecdbd417c91cf9f296dc6b265d6f953790e30a7b751385fe8c28a9b1ce3"}