{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LMV5GEPOIXOLHMKKPU35JIRDUU","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":"9a4dec9a2fe8110009a98c4bdfc82712bc85c6f84045f73788f8a557c206e227","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-12T08:02:23Z","title_canon_sha256":"380ccf930d7891ffcff9fbf295a231b7921128a74ada1e7c172d54587b178b3b"},"schema_version":"1.0","source":{"id":"2202.06009","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06009","created_at":"2026-07-05T04:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06009v3","created_at":"2026-07-05T04:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06009","created_at":"2026-07-05T04:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"LMV5GEPOIXOL","created_at":"2026-07-05T04:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"LMV5GEPOIXOLHMKK","created_at":"2026-07-05T04:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"LMV5GEPO","created_at":"2026-07-05T04:25:15Z"}],"graph_snapshots":[{"event_id":"sha256:21747fd89fe4396ee19dce73e05735c7bb39be7c736a31868e0259ec76f00cda","target":"graph","created_at":"2026-07-05T04:25:15Z","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/2202.06009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"1-bit gradient compression and local steps are two representative techniques that enable drastic communication reduction in distributed SGD. Their benefits, however, remain an open question on Adam-based large model pre-training (e.g. BERT and GPT). In this paper, we demonstrate the non-linearity in Adam causes slow convergence even when 1-bit compression or local steps are individually applied. To alleviate this limitation, we propose 0/1 Adam that linearizes each Adam step via approximating its optimizer states using their stale estimates and linear correlation. 0/1 Adam performs an Adam-lik","authors_text":"Christopher De Sa, Conglong Li, Minjia Zhang, Yucheng Lu, Yuxiong He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-12T08:02:23Z","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06009","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":"sha256:418c9e9cb72a43ff0199cb13695cd3152090212a50101f7121ff5f73fcbabd25","target":"record","created_at":"2026-07-05T04:25:15Z","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":"9a4dec9a2fe8110009a98c4bdfc82712bc85c6f84045f73788f8a557c206e227","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-12T08:02:23Z","title_canon_sha256":"380ccf930d7891ffcff9fbf295a231b7921128a74ada1e7c172d54587b178b3b"},"schema_version":"1.0","source":{"id":"2202.06009","kind":"arxiv","version":3}},"canonical_sha256":"5b2bd311ee45dcb3b14a7d37d4a223a52ed2fde93d57e5b3f32d3a67b0c47613","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b2bd311ee45dcb3b14a7d37d4a223a52ed2fde93d57e5b3f32d3a67b0c47613","first_computed_at":"2026-07-05T04:25:15.763498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:15.763498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdDR3GDN/hE/fsy+ktYeVSJdmoFr8I1Rhi60FcI2l0O4f1b9i4/n3SZVWBJvbZnfWwsb70/isf2C4X8lBNQ3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:15.764024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06009","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:418c9e9cb72a43ff0199cb13695cd3152090212a50101f7121ff5f73fcbabd25","sha256:21747fd89fe4396ee19dce73e05735c7bb39be7c736a31868e0259ec76f00cda"],"state_sha256":"649ccd6ca00a88ec926ad61677c12ccd55adda6c5bb2ed516f60e753a541f313"}