{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KSSC3NVU26CYB6N6PFDUCMIMLT","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":"5439a593f75ed4001ecff6838226bf505165f79575e7e691dbf539f2d45f70a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:58:53Z","title_canon_sha256":"eaf0ebf5f357e671a4e59ade89415ddfef13243a18049ee42deb3efa1bb4b110"},"schema_version":"1.0","source":{"id":"2410.08198","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08198","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08198v3","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08198","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"KSSC3NVU26CY","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_16","alias_value":"KSSC3NVU26CYB6N6","created_at":"2026-07-05T11:19:49Z"},{"alias_kind":"pith_short_8","alias_value":"KSSC3NVU","created_at":"2026-07-05T11:19:49Z"}],"graph_snapshots":[{"event_id":"sha256:9cd3d9185f50a49afa29f6f69cd7c452ca1fec98eca99a67041cf67e0621fb49","target":"graph","created_at":"2026-07-05T11:19:49Z","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/2410.08198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adam outperforms SGD when training language models. Yet this advantage is not well-understood theoretically -- previous convergence analysis for Adam and SGD mainly focuses on the number of steps $T$ and is already minimax-optimal in non-convex cases, which are both $\\widetilde{O}(T^{-1/4})$. In this work, we argue that the exploitation of nice $\\ell_\\infty$-geometry is the key advantage of Adam over SGD. More specifically, we give a new convergence analysis for Adam under novel assumptions that loss is smooth under $\\ell_\\infty$-geometry rather than the more common $\\ell_2$-geometry, which yi","authors_text":"Mohamad Amin Mohamadi, Shuo Xie, Zhiyuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:58:53Z","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08198","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":"sha256:4ee0175457c5e132d497b383ac5156b88e8e18ad6cee2daac1176d5bd0c6b225","target":"record","created_at":"2026-07-05T11:19:49Z","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":"5439a593f75ed4001ecff6838226bf505165f79575e7e691dbf539f2d45f70a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:58:53Z","title_canon_sha256":"eaf0ebf5f357e671a4e59ade89415ddfef13243a18049ee42deb3efa1bb4b110"},"schema_version":"1.0","source":{"id":"2410.08198","kind":"arxiv","version":3}},"canonical_sha256":"54a42db6b4d78580f9be794741310c5cc2e78416472cdde458660eb553222471","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a42db6b4d78580f9be794741310c5cc2e78416472cdde458660eb553222471","first_computed_at":"2026-07-05T11:19:49.677231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:49.677231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fjN9MEEwCuIwxjSowCU+3RZa9SzMYZ82dRJIZau408Dq35E8iWb4Uxr6Y/P80J5KRyxHArQhI9hhJh8JEdUNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:49.677702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08198","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ee0175457c5e132d497b383ac5156b88e8e18ad6cee2daac1176d5bd0c6b225","sha256:9cd3d9185f50a49afa29f6f69cd7c452ca1fec98eca99a67041cf67e0621fb49"],"state_sha256":"deca598a1f4127134c877e2a0e8803275dab4e6ea1484060fbb2b01422c0a08d"}