{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JXMVLSVZ7B4A7F3JLM5PIYYILY","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":"39621e4a5702f2758ab584ed0e53cf446646b46bdec75751d49d22f4da1a8cb5","cross_cats_sorted":["cs.CV","cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-01T18:04:31Z","title_canon_sha256":"af88ba0d8150a55a7cb0eac82afb70a51ef80b534d39ccdf8425d27d0cd268aa"},"schema_version":"1.0","source":{"id":"1711.00489","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00489","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00489v2","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00489","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"JXMVLSVZ7B4A","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JXMVLSVZ7B4A7F3J","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JXMVLSVZ","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:7d5068929a07627ce5d1204fd138d82d8b439902ff6148fd5641d0d106304220","target":"graph","created_at":"2026-05-18T00:22:39Z","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"},"paper":{"abstract_excerpt":"It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic gradient descent (SGD), SGD with momentum, Nesterov momentum, and Adam. It reaches equivalent test accuracies after the same number of training epochs, but with fewer parameter updates, leading to greater parallelism and shorter training times. We can further reduce the number of parameter updates by increasing the learning rate $\\epsilon$ and scaling the bat","authors_text":"Chris Ying, Pieter-Jan Kindermans, Quoc V. Le, Samuel L. Smith","cross_cats":["cs.CV","cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-01T18:04:31Z","title":"Don't Decay the Learning Rate, Increase the Batch Size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00489","kind":"arxiv","version":2},"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:bd510d71ca4b7d34554903f18d34753f29becca9d98074b29bf529e9125b4eba","target":"record","created_at":"2026-05-18T00:22:39Z","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":"39621e4a5702f2758ab584ed0e53cf446646b46bdec75751d49d22f4da1a8cb5","cross_cats_sorted":["cs.CV","cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-01T18:04:31Z","title_canon_sha256":"af88ba0d8150a55a7cb0eac82afb70a51ef80b534d39ccdf8425d27d0cd268aa"},"schema_version":"1.0","source":{"id":"1711.00489","kind":"arxiv","version":2}},"canonical_sha256":"4dd955cab9f8780f97695b3af463085e19ab1f7da6f922959e527872d10dff1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dd955cab9f8780f97695b3af463085e19ab1f7da6f922959e527872d10dff1e","first_computed_at":"2026-05-18T00:22:39.281193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:39.281193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1pP9i0ZXlAi88HeXvhwF0r66J0FAYJK9LthgXfiwaaVrGj8cAQL9ncn0PFjT0f8xdEppB/pTSBtXfx6DVpIMAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:39.281673Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00489","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd510d71ca4b7d34554903f18d34753f29becca9d98074b29bf529e9125b4eba","sha256:7d5068929a07627ce5d1204fd138d82d8b439902ff6148fd5641d0d106304220"],"state_sha256":"639b10615b1eed11474946d569750a736e62592919f04e71d6102b4d3b2b43ce"}