{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:JF7L4UFSHJ62VTZWOWX3VOUQJG","short_pith_number":"pith:JF7L4UFS","schema_version":"1.0","canonical_sha256":"497ebe50b23a7daacf3675afbaba9049a30d774664f31c83bcca8a4482c5862f","source":{"kind":"arxiv","id":"1312.1666","version":2},"attestation_state":"computed","paper":{"title":"Semi-Stochastic Gradient Descent Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC"],"primary_cat":"stat.ML","authors_text":"Jakub Kone\\v{c}n\\'y, Peter Richt\\'arik","submitted_at":"2013-12-05T20:04:52Z","abstract_excerpt":"In this paper we study the problem of minimizing the average of a large number ($n$) of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic Gradient Descent), which runs for one or several epochs in each of which a single full gradient and a random number of stochastic gradients is computed, following a geometric law. The total work needed for the method to output an $\\varepsilon$-accurate solution in expectation, measured in the number of passes over data, or equivalently, in units equivalent to the computation of a single gradient of the loss, is $O((\\kappa/n)\\log(1/"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1312.1666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-12-05T20:04:52Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.OC"],"title_canon_sha256":"153faab22d0d0b09a05ac7f6ad65cc14763cf3fbf58602cc36c2e38bbe3abe1c","abstract_canon_sha256":"c39968e4f38a929b416cc906390eddc166039c35ccf671375a44daeb85b5cb8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:48:06.889360Z","signature_b64":"X5ILiM5FfWc8PSrCVqS1FmasFgAUo9CszH+0pPL9KtI9UMWeyt7ziw/d04wMhL8LFGb78wTjQ3DRV5sJfeI5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"497ebe50b23a7daacf3675afbaba9049a30d774664f31c83bcca8a4482c5862f","last_reissued_at":"2026-05-18T01:48:06.888818Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:48:06.888818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Stochastic Gradient Descent Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC"],"primary_cat":"stat.ML","authors_text":"Jakub Kone\\v{c}n\\'y, Peter Richt\\'arik","submitted_at":"2013-12-05T20:04:52Z","abstract_excerpt":"In this paper we study the problem of minimizing the average of a large number ($n$) of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic Gradient Descent), which runs for one or several epochs in each of which a single full gradient and a random number of stochastic gradients is computed, following a geometric law. The total work needed for the method to output an $\\varepsilon$-accurate solution in expectation, measured in the number of passes over data, or equivalently, in units equivalent to the computation of a single gradient of the loss, is $O((\\kappa/n)\\log(1/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.1666","kind":"arxiv","version":2},"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":"1312.1666","created_at":"2026-05-18T01:48:06.888912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.1666v2","created_at":"2026-05-18T01:48:06.888912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.1666","created_at":"2026-05-18T01:48:06.888912+00:00"},{"alias_kind":"pith_short_12","alias_value":"JF7L4UFSHJ62","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_16","alias_value":"JF7L4UFSHJ62VTZW","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_8","alias_value":"JF7L4UFS","created_at":"2026-05-18T12:27:49.015174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":145,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG","json":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG.json","graph_json":"https://pith.science/api/pith-number/JF7L4UFSHJ62VTZWOWX3VOUQJG/graph.json","events_json":"https://pith.science/api/pith-number/JF7L4UFSHJ62VTZWOWX3VOUQJG/events.json","paper":"https://pith.science/paper/JF7L4UFS"},"agent_actions":{"view_html":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG","download_json":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG.json","view_paper":"https://pith.science/paper/JF7L4UFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.1666&json=true","fetch_graph":"https://pith.science/api/pith-number/JF7L4UFSHJ62VTZWOWX3VOUQJG/graph.json","fetch_events":"https://pith.science/api/pith-number/JF7L4UFSHJ62VTZWOWX3VOUQJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG/action/storage_attestation","attest_author":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG/action/author_attestation","sign_citation":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG/action/citation_signature","submit_replication":"https://pith.science/pith/JF7L4UFSHJ62VTZWOWX3VOUQJG/action/replication_record"}},"created_at":"2026-05-18T01:48:06.888912+00:00","updated_at":"2026-05-18T01:48:06.888912+00:00"}