{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GOXHU4LFZRP45WF5DVXWEIMGED","short_pith_number":"pith:GOXHU4LF","schema_version":"1.0","canonical_sha256":"33ae7a7165cc5fced8bd1d6f62218620c26bdb44e2bbb91113c383a56be90ce1","source":{"kind":"arxiv","id":"1605.08882","version":3},"attestation_state":"computed","paper":{"title":"Optimal Rates for Multi-pass Stochastic Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junhong Lin, Lorenzo Rosasco","submitted_at":"2016-05-28T12:11:22Z","abstract_excerpt":"We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the mini-batch size. In particular, we consider the square loss and show that for a universal step-size choice, the number of passes acts as a regularization parameter, and optimal finite sample bounds can be achieved by early-stopping. Moreover, we show that larger step-sizes are allowed when considering mini-batches. Our analysis is based on a unifying approach, en"},"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":"1605.08882","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-28T12:11:22Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"d047fb2901a248a09962a958761b7d6527701619d9e6880e6ef14260047d47cf","abstract_canon_sha256":"9ad0aae59e40e5070a1b12823a9cb8c76e08b350ebe1607c13b8d020fbbc93ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:15.035493Z","signature_b64":"O9sGLJbtvLKg0MdVjE/qDaLYP8NJvh8xFOafT/3bIaa+42Tun4mVvz45vrIlpQNQuGBBrU7u4mE3tAdlnVRvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ae7a7165cc5fced8bd1d6f62218620c26bdb44e2bbb91113c383a56be90ce1","last_reissued_at":"2026-05-17T23:51:15.034911Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:15.034911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Rates for Multi-pass Stochastic Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junhong Lin, Lorenzo Rosasco","submitted_at":"2016-05-28T12:11:22Z","abstract_excerpt":"We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the mini-batch size. In particular, we consider the square loss and show that for a universal step-size choice, the number of passes acts as a regularization parameter, and optimal finite sample bounds can be achieved by early-stopping. Moreover, we show that larger step-sizes are allowed when considering mini-batches. Our analysis is based on a unifying approach, en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08882","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":"1605.08882","created_at":"2026-05-17T23:51:15.035010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08882v3","created_at":"2026-05-17T23:51:15.035010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08882","created_at":"2026-05-17T23:51:15.035010+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOXHU4LFZRP4","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOXHU4LFZRP45WF5","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOXHU4LF","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED","json":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED.json","graph_json":"https://pith.science/api/pith-number/GOXHU4LFZRP45WF5DVXWEIMGED/graph.json","events_json":"https://pith.science/api/pith-number/GOXHU4LFZRP45WF5DVXWEIMGED/events.json","paper":"https://pith.science/paper/GOXHU4LF"},"agent_actions":{"view_html":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED","download_json":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED.json","view_paper":"https://pith.science/paper/GOXHU4LF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08882&json=true","fetch_graph":"https://pith.science/api/pith-number/GOXHU4LFZRP45WF5DVXWEIMGED/graph.json","fetch_events":"https://pith.science/api/pith-number/GOXHU4LFZRP45WF5DVXWEIMGED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED/action/storage_attestation","attest_author":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED/action/author_attestation","sign_citation":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED/action/citation_signature","submit_replication":"https://pith.science/pith/GOXHU4LFZRP45WF5DVXWEIMGED/action/replication_record"}},"created_at":"2026-05-17T23:51:15.035010+00:00","updated_at":"2026-05-17T23:51:15.035010+00:00"}