{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S5U3EE5HEMUUEJRRAJTJNKERZ4","short_pith_number":"pith:S5U3EE5H","schema_version":"1.0","canonical_sha256":"9769b213a72329422631026696a891cf3d0b3a5a151f9c3b31390fcc60dddb4e","source":{"kind":"arxiv","id":"1909.00843","version":1},"attestation_state":"computed","paper":{"title":"Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Liaw, Nicholas J. A. Harvey, Sikander Randhawa","submitted_at":"2019-09-02T19:47:47Z","abstract_excerpt":"We consider stochastic gradient descent algorithms for minimizing a non-smooth, strongly-convex function. Several forms of this algorithm, including suffix averaging, are known to achieve the optimal $O(1/T)$ convergence rate in expectation. We consider a simple, non-uniform averaging strategy of Lacoste-Julien et al. (2011) and prove that it achieves the optimal $O(1/T)$ convergence rate with high probability. Our proof uses a recently developed generalization of Freedman's inequality. Finally, we compare several of these algorithms experimentally and show that this non-uniform averaging stra"},"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":"1909.00843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-02T19:47:47Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"39b22bff3a4219a6f75576d686f133fc2378fdf4062d07411527fb35538ff41d","abstract_canon_sha256":"4fd092f3bc7d2a783822d8b4b3a53b4b0526bebf3b16fe94d2fa967d85931856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:13.261715Z","signature_b64":"s3MaKkML+UioQbNh/cUbv/FNrk4tPJLYv/c8vX1fbQKozBv/vTw1c8mIqDgWe08B8Inok/aO/Vwce6soiT9QBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9769b213a72329422631026696a891cf3d0b3a5a151f9c3b31390fcc60dddb4e","last_reissued_at":"2026-07-05T00:01:13.261348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:13.261348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Liaw, Nicholas J. A. Harvey, Sikander Randhawa","submitted_at":"2019-09-02T19:47:47Z","abstract_excerpt":"We consider stochastic gradient descent algorithms for minimizing a non-smooth, strongly-convex function. Several forms of this algorithm, including suffix averaging, are known to achieve the optimal $O(1/T)$ convergence rate in expectation. We consider a simple, non-uniform averaging strategy of Lacoste-Julien et al. (2011) and prove that it achieves the optimal $O(1/T)$ convergence rate with high probability. Our proof uses a recently developed generalization of Freedman's inequality. Finally, we compare several of these algorithms experimentally and show that this non-uniform averaging stra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00843","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.00843/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.00843","created_at":"2026-07-05T00:01:13.261412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00843v1","created_at":"2026-07-05T00:01:13.261412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00843","created_at":"2026-07-05T00:01:13.261412+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5U3EE5HEMUU","created_at":"2026-07-05T00:01:13.261412+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5U3EE5HEMUUEJRR","created_at":"2026-07-05T00:01:13.261412+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5U3EE5H","created_at":"2026-07-05T00:01:13.261412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31309","citing_title":"Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20999","citing_title":"Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07239","citing_title":"Sample Complexity of Stochastic Optimization with Integer Variables","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4","json":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4.json","graph_json":"https://pith.science/api/pith-number/S5U3EE5HEMUUEJRRAJTJNKERZ4/graph.json","events_json":"https://pith.science/api/pith-number/S5U3EE5HEMUUEJRRAJTJNKERZ4/events.json","paper":"https://pith.science/paper/S5U3EE5H"},"agent_actions":{"view_html":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4","download_json":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4.json","view_paper":"https://pith.science/paper/S5U3EE5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00843&json=true","fetch_graph":"https://pith.science/api/pith-number/S5U3EE5HEMUUEJRRAJTJNKERZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/S5U3EE5HEMUUEJRRAJTJNKERZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4/action/storage_attestation","attest_author":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4/action/author_attestation","sign_citation":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4/action/citation_signature","submit_replication":"https://pith.science/pith/S5U3EE5HEMUUEJRRAJTJNKERZ4/action/replication_record"}},"created_at":"2026-07-05T00:01:13.261412+00:00","updated_at":"2026-07-05T00:01:13.261412+00:00"}