{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QUFRB76BTSOTWJY4WXOXUZUIS4","short_pith_number":"pith:QUFRB76B","schema_version":"1.0","canonical_sha256":"850b10ffc19c9d3b271cb5dd7a6688970cf5fd46b1e5e0f4c750acdad2096d78","source":{"kind":"arxiv","id":"1907.04232","version":2},"attestation_state":"computed","paper":{"title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sebastian U. Stich","submitted_at":"2019-07-09T15:14:25Z","abstract_excerpt":"In this note we give a simple proof for the convergence of stochastic gradient (SGD) methods on $\\mu$-convex functions under a (milder than standard) $L$-smoothness assumption. We show that for carefully chosen stepsizes SGD converges after $T$ iterations as $O\\left( LR^2 \\exp \\bigl[-\\frac{\\mu}{4L}T\\bigr] + \\frac{\\sigma^2}{\\mu T} \\right)$ where $\\sigma^2$ measures the variance in the stochastic noise. For deterministic gradient descent (GD) and SGD in the interpolation setting we have $\\sigma^2 =0$ and we recover the exponential convergence rate. The bound matches with the best known iteration"},"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":"1907.04232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T15:14:25Z","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"84d49f36be062b17134633e0ac4b37dc314c6b53c552727dc5f12d53a2fd23a0","abstract_canon_sha256":"0baa3ce648f927d8c7e0257e34dec2f7b63356f1b2327bf040aa654ed9b7cb6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:58.092397Z","signature_b64":"aVwYCb9KVL5G6eBWRhcIVuwos7ozMqaa5a+K+9z1dVAzzLPNVmnY781rhHEGdixB1VXc/9LcIR15/ZAt1+T7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850b10ffc19c9d3b271cb5dd7a6688970cf5fd46b1e5e0f4c750acdad2096d78","last_reissued_at":"2026-07-05T00:27:58.091807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:58.091807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sebastian U. Stich","submitted_at":"2019-07-09T15:14:25Z","abstract_excerpt":"In this note we give a simple proof for the convergence of stochastic gradient (SGD) methods on $\\mu$-convex functions under a (milder than standard) $L$-smoothness assumption. We show that for carefully chosen stepsizes SGD converges after $T$ iterations as $O\\left( LR^2 \\exp \\bigl[-\\frac{\\mu}{4L}T\\bigr] + \\frac{\\sigma^2}{\\mu T} \\right)$ where $\\sigma^2$ measures the variance in the stochastic noise. For deterministic gradient descent (GD) and SGD in the interpolation setting we have $\\sigma^2 =0$ and we recover the exponential convergence rate. The bound matches with the best known iteration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04232","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1907.04232/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":"1907.04232","created_at":"2026-07-05T00:27:58.091874+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04232v2","created_at":"2026-07-05T00:27:58.091874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04232","created_at":"2026-07-05T00:27:58.091874+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUFRB76BTSOT","created_at":"2026-07-05T00:27:58.091874+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUFRB76BTSOTWJY4","created_at":"2026-07-05T00:27:58.091874+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUFRB76B","created_at":"2026-07-05T00:27:58.091874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14970","citing_title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01527","citing_title":"Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18718","citing_title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16875","citing_title":"Stochastic Optimization and Data Science","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10205","citing_title":"Unveiling High-Probability Generalization in Decentralized SGD","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01701","citing_title":"Stability and Generalization for Decentralized Markov SGD","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4","json":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4.json","graph_json":"https://pith.science/api/pith-number/QUFRB76BTSOTWJY4WXOXUZUIS4/graph.json","events_json":"https://pith.science/api/pith-number/QUFRB76BTSOTWJY4WXOXUZUIS4/events.json","paper":"https://pith.science/paper/QUFRB76B"},"agent_actions":{"view_html":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4","download_json":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4.json","view_paper":"https://pith.science/paper/QUFRB76B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04232&json=true","fetch_graph":"https://pith.science/api/pith-number/QUFRB76BTSOTWJY4WXOXUZUIS4/graph.json","fetch_events":"https://pith.science/api/pith-number/QUFRB76BTSOTWJY4WXOXUZUIS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4/action/storage_attestation","attest_author":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4/action/author_attestation","sign_citation":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4/action/citation_signature","submit_replication":"https://pith.science/pith/QUFRB76BTSOTWJY4WXOXUZUIS4/action/replication_record"}},"created_at":"2026-07-05T00:27:58.091874+00:00","updated_at":"2026-07-05T00:27:58.091874+00:00"}