{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VZRHY5IPQIHVH2BYUGAYRNSNZ2","short_pith_number":"pith:VZRHY5IP","schema_version":"1.0","canonical_sha256":"ae627c750f820f53e838a18188b64dce95a4f94fd1aec8e78d9e001c88c0ca5c","source":{"kind":"arxiv","id":"1708.07120","version":3},"attestation_state":"computed","paper":{"title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Leslie N. Smith, Nicholay Topin","submitted_at":"2017-08-23T17:51:57Z","abstract_excerpt":"In this paper, we describe a phenomenon, which we named \"super-convergence\", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to understanding why deep networks generalize well. One of the key elements of super-convergence is training with one learning rate cycle and a large maximum learning rate. A primary insight that allows super-convergence training is that large learning rates regularize the training, hence requiring a reduction of all other forms of regularization in order to preserve an "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1708.07120","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-23T17:51:57Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"1592d94ff8017f2d5935b098dc5a061b0fa30be80da22623b27c03e01fbba243","abstract_canon_sha256":"553983670dcc6aa3f43d774c3cb3e359ceba4d31ba984660e482b65a8620b4df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:47.106455Z","signature_b64":"v0tZSSDZ6z8TIl9nTt2MuGFAjprRpXPdsAN7Zm6SSPinzTREsr7Tf/HZUJkKCQYKw27OMk++/J3S+TdtcJf2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae627c750f820f53e838a18188b64dce95a4f94fd1aec8e78d9e001c88c0ca5c","last_reissued_at":"2026-05-18T00:15:47.105803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:47.105803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Leslie N. Smith, Nicholay Topin","submitted_at":"2017-08-23T17:51:57Z","abstract_excerpt":"In this paper, we describe a phenomenon, which we named \"super-convergence\", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to understanding why deep networks generalize well. One of the key elements of super-convergence is training with one learning rate cycle and a large maximum learning rate. A primary insight that allows super-convergence training is that large learning rates regularize the training, hence requiring a reduction of all other forms of regularization in order to preserve an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07120","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.07120","created_at":"2026-05-18T00:15:47.105913+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.07120v3","created_at":"2026-05-18T00:15:47.105913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07120","created_at":"2026-05-18T00:15:47.105913+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZRHY5IPQIHV","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZRHY5IPQIHVH2BY","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZRHY5IP","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2606.05186","citing_title":"Staged Factorial Screening for Budget-Constrained Micro-Pretraining","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":202,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17866","citing_title":"Data-Driven Calibration of Large Liquid Detectors with Unsupervised Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2509.13821","citing_title":"Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10791","citing_title":"OmniMol: Transferring Particle Physics Knowledge to Molecular Dynamics with Point-Edge Transformers","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06382","citing_title":"Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28921","citing_title":"Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural Network Training","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06742","citing_title":"Bayesian Modeling and Prediction of Generalized Contact Matrices","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2","json":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2.json","graph_json":"https://pith.science/api/pith-number/VZRHY5IPQIHVH2BYUGAYRNSNZ2/graph.json","events_json":"https://pith.science/api/pith-number/VZRHY5IPQIHVH2BYUGAYRNSNZ2/events.json","paper":"https://pith.science/paper/VZRHY5IP"},"agent_actions":{"view_html":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2","download_json":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2.json","view_paper":"https://pith.science/paper/VZRHY5IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.07120&json=true","fetch_graph":"https://pith.science/api/pith-number/VZRHY5IPQIHVH2BYUGAYRNSNZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/VZRHY5IPQIHVH2BYUGAYRNSNZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2/action/storage_attestation","attest_author":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2/action/author_attestation","sign_citation":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2/action/citation_signature","submit_replication":"https://pith.science/pith/VZRHY5IPQIHVH2BYUGAYRNSNZ2/action/replication_record"}},"created_at":"2026-05-18T00:15:47.105913+00:00","updated_at":"2026-05-18T00:15:47.105913+00:00"}