{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:X6C7HE6GW3MZ7Z3NDLH3MRE6VI","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":"0129bd50d66cbe7b561b5269da5d44840bfc61ba1cee2cd8c586e8fd5d499f19","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-22T04:50:55Z","title_canon_sha256":"9406e39837368c7f5ed49513798826363b768aeffd47ad72a4ab6af72d48d655"},"schema_version":"1.0","source":{"id":"1808.07217","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07217","created_at":"2026-07-05T00:40:53Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07217v6","created_at":"2026-07-05T00:40:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07217","created_at":"2026-07-05T00:40:53Z"},{"alias_kind":"pith_short_12","alias_value":"X6C7HE6GW3MZ","created_at":"2026-07-05T00:40:53Z"},{"alias_kind":"pith_short_16","alias_value":"X6C7HE6GW3MZ7Z3N","created_at":"2026-07-05T00:40:53Z"},{"alias_kind":"pith_short_8","alias_value":"X6C7HE6G","created_at":"2026-07-05T00:40:53Z"}],"graph_snapshots":[{"event_id":"sha256:c5ec9515dfab5c2b97f238646294a93993fd90530af62fcd1cb5c24178cce9ab","target":"graph","created_at":"2026-07-05T00:40:53Z","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/1808.07217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However, progress faces a major roadblock, as models trained with large batches often do not generalize well, i.e. they do not show good accuracy on new data. As a remedy, we propose a \\emph{post-local} SGD and show that it significantly improves the generalization performance compared to large-batch training on standard benchmarks while enjoying the same efficiency (time-","authors_text":"Kumar Kshitij Patel, Martin Jaggi, Sebastian U. Stich, Tao Lin","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-22T04:50:55Z","title":"Don't Use Large Mini-Batches, Use Local SGD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07217","kind":"arxiv","version":6},"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":"sha256:3b3ad391c2b0ac39d4d0449ea766f7f480514611c0f17ea04baec13f2381e299","target":"record","created_at":"2026-07-05T00:40:53Z","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":"0129bd50d66cbe7b561b5269da5d44840bfc61ba1cee2cd8c586e8fd5d499f19","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-22T04:50:55Z","title_canon_sha256":"9406e39837368c7f5ed49513798826363b768aeffd47ad72a4ab6af72d48d655"},"schema_version":"1.0","source":{"id":"1808.07217","kind":"arxiv","version":6}},"canonical_sha256":"bf85f393c6b6d99fe76d1acfb6449eaa312766b32db4a95759d6b8ee9c74d611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf85f393c6b6d99fe76d1acfb6449eaa312766b32db4a95759d6b8ee9c74d611","first_computed_at":"2026-07-05T00:40:53.187609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:53.187609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"glEz0gsypUZFSgy8Qc5iftJel5y9vm10w7SupUVctGjnNQ55XsHRaa4mqxN+Tn69UgtwaXv7SzBAM8sMYEW4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:53.188114Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07217","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b3ad391c2b0ac39d4d0449ea766f7f480514611c0f17ea04baec13f2381e299","sha256:c5ec9515dfab5c2b97f238646294a93993fd90530af62fcd1cb5c24178cce9ab"],"state_sha256":"ea86badabff79c183fd5b942c770c34ecf5f7dfb0dc06e42f92c499830b1a453"}