{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:YIJVHO64F5QZIT76XSNXNG4R6J","short_pith_number":"pith:YIJVHO64","schema_version":"1.0","canonical_sha256":"c21353bbdc2f61944ffebc9b769b91f25c8f6e549d3253e7bb84658cb5acdc53","source":{"kind":"arxiv","id":"1310.5715","version":5},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","math.OC","stat.ML"],"primary_cat":"math.NA","authors_text":"Deanna Needell, Nathan Srebro, Rachel Ward","submitted_at":"2013-10-21T20:15:44Z","abstract_excerpt":"We obtain an improved finite-sample guarantee on the linear convergence of stochastic gradient descent for smooth and strongly convex objectives, improving from a quadratic dependence on the conditioning $(L/\\mu)^2$ (where $L$ is a bound on the smoothness and $\\mu$ on the strong convexity) to a linear dependence on $L/\\mu$. Furthermore, we show how reweighting the sampling distribution (i.e. importance sampling) is necessary in order to further improve convergence, and obtain a linear dependence in the average smoothness, dominating previous results. We also discuss importance sampling for SGD"},"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":"1310.5715","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2013-10-21T20:15:44Z","cross_cats_sorted":["cs.CV","cs.LG","math.OC","stat.ML"],"title_canon_sha256":"b15e4acbf36aba63bb5e51c7470ee3e830fae12f5ebad2e8ff45f3579f9c0085","abstract_canon_sha256":"72fb71284233442330c5adf64d2860864f6558dfba2e5f8964734dff74671577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:29:17.602914Z","signature_b64":"Out7bB7qNB7Uoa8Dl3Siz8Uw3N6/9OAr6ylSWpGv/MtPyd2LZiAkZTulbX6vYEACINFHTwLUCJlQHRnkqpV2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c21353bbdc2f61944ffebc9b769b91f25c8f6e549d3253e7bb84658cb5acdc53","last_reissued_at":"2026-05-18T02:29:17.602499Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:29:17.602499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","math.OC","stat.ML"],"primary_cat":"math.NA","authors_text":"Deanna Needell, Nathan Srebro, Rachel Ward","submitted_at":"2013-10-21T20:15:44Z","abstract_excerpt":"We obtain an improved finite-sample guarantee on the linear convergence of stochastic gradient descent for smooth and strongly convex objectives, improving from a quadratic dependence on the conditioning $(L/\\mu)^2$ (where $L$ is a bound on the smoothness and $\\mu$ on the strong convexity) to a linear dependence on $L/\\mu$. Furthermore, we show how reweighting the sampling distribution (i.e. importance sampling) is necessary in order to further improve convergence, and obtain a linear dependence in the average smoothness, dominating previous results. We also discuss importance sampling for SGD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1310.5715","kind":"arxiv","version":5},"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":"1310.5715","created_at":"2026-05-18T02:29:17.602558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1310.5715v5","created_at":"2026-05-18T02:29:17.602558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1310.5715","created_at":"2026-05-18T02:29:17.602558+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIJVHO64F5QZ","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIJVHO64F5QZIT76","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIJVHO64","created_at":"2026-05-18T12:28:06.772260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":109,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J","json":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J.json","graph_json":"https://pith.science/api/pith-number/YIJVHO64F5QZIT76XSNXNG4R6J/graph.json","events_json":"https://pith.science/api/pith-number/YIJVHO64F5QZIT76XSNXNG4R6J/events.json","paper":"https://pith.science/paper/YIJVHO64"},"agent_actions":{"view_html":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J","download_json":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J.json","view_paper":"https://pith.science/paper/YIJVHO64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1310.5715&json=true","fetch_graph":"https://pith.science/api/pith-number/YIJVHO64F5QZIT76XSNXNG4R6J/graph.json","fetch_events":"https://pith.science/api/pith-number/YIJVHO64F5QZIT76XSNXNG4R6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J/action/storage_attestation","attest_author":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J/action/author_attestation","sign_citation":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J/action/citation_signature","submit_replication":"https://pith.science/pith/YIJVHO64F5QZIT76XSNXNG4R6J/action/replication_record"}},"created_at":"2026-05-18T02:29:17.602558+00:00","updated_at":"2026-05-18T02:29:17.602558+00:00"}