{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FC3Y7KFIVQLJDQMJVCZWD3RYCY","short_pith_number":"pith:FC3Y7KFI","schema_version":"1.0","canonical_sha256":"28b78fa8a8ac1691c189a8b361ee381600084d0cdc61da77af823e49c7382f76","source":{"kind":"arxiv","id":"1810.07288","version":3},"attestation_state":"computed","paper":{"title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francis Bach, Mark Schmidt, Sharan Vaswani","submitted_at":"2018-10-16T21:48:11Z","abstract_excerpt":"Modern machine learning focuses on highly expressive models that are able to fit or interpolate the data completely, resulting in zero training loss. For such models, we show that the stochastic gradients of common loss functions satisfy a strong growth condition. Under this condition, we prove that constant step-size stochastic gradient descent (SGD) with Nesterov acceleration matches the convergence rate of the deterministic accelerated method for both convex and strongly-convex functions. We also show that this condition implies that SGD can find a first-order stationary point as efficientl"},"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":"1810.07288","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T21:48:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e78b07faf8adbcdb5acbc525d636d06166c3881e4a4d282c5ef70e299a5ad0e","abstract_canon_sha256":"0f0c110a50add36a5aa8f88f2f3754463e2fe6df878a7806860d214615d5b6f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.293972Z","signature_b64":"waNZd1UC5sYGxwtvmGTnO/Q9vXJztXGtviv8PSRmWm1OdSIexwIusVoLR3Is6Qqg09OaUmCQ0uEDh37bS8l8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b78fa8a8ac1691c189a8b361ee381600084d0cdc61da77af823e49c7382f76","last_reissued_at":"2026-05-17T23:49:17.293219Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.293219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francis Bach, Mark Schmidt, Sharan Vaswani","submitted_at":"2018-10-16T21:48:11Z","abstract_excerpt":"Modern machine learning focuses on highly expressive models that are able to fit or interpolate the data completely, resulting in zero training loss. For such models, we show that the stochastic gradients of common loss functions satisfy a strong growth condition. Under this condition, we prove that constant step-size stochastic gradient descent (SGD) with Nesterov acceleration matches the convergence rate of the deterministic accelerated method for both convex and strongly-convex functions. We also show that this condition implies that SGD can find a first-order stationary point as efficientl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07288","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":"1810.07288","created_at":"2026-05-17T23:49:17.293371+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07288v3","created_at":"2026-05-17T23:49:17.293371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07288","created_at":"2026-05-17T23:49:17.293371+00:00"},{"alias_kind":"pith_short_12","alias_value":"FC3Y7KFIVQLJ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FC3Y7KFIVQLJDQMJ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FC3Y7KFI","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.27142","citing_title":"Estimation of High Dimensional Bounded Discrete Graphical Models via Regularized Generalized Score Matching","ref_index":250,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10089","citing_title":"A Theory on Flow Matching with Neural Networks","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY","json":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY.json","graph_json":"https://pith.science/api/pith-number/FC3Y7KFIVQLJDQMJVCZWD3RYCY/graph.json","events_json":"https://pith.science/api/pith-number/FC3Y7KFIVQLJDQMJVCZWD3RYCY/events.json","paper":"https://pith.science/paper/FC3Y7KFI"},"agent_actions":{"view_html":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY","download_json":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY.json","view_paper":"https://pith.science/paper/FC3Y7KFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07288&json=true","fetch_graph":"https://pith.science/api/pith-number/FC3Y7KFIVQLJDQMJVCZWD3RYCY/graph.json","fetch_events":"https://pith.science/api/pith-number/FC3Y7KFIVQLJDQMJVCZWD3RYCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY/action/storage_attestation","attest_author":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY/action/author_attestation","sign_citation":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY/action/citation_signature","submit_replication":"https://pith.science/pith/FC3Y7KFIVQLJDQMJVCZWD3RYCY/action/replication_record"}},"created_at":"2026-05-17T23:49:17.293371+00:00","updated_at":"2026-05-17T23:49:17.293371+00:00"}