{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GA7TUOQKJD32J4YRORXQAALREL","short_pith_number":"pith:GA7TUOQK","schema_version":"1.0","canonical_sha256":"303f3a3a0a48f7a4f311746f00017122eddf295bb032e96c8e631186c0ec3b28","source":{"kind":"arxiv","id":"2410.05106","version":3},"attestation_state":"computed","paper":{"title":"Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alain Durmus, Alexey Naumov, Denis Belomestny, Eric Moulines, Marina Sheshukova, Sergey Samsonov","submitted_at":"2024-10-07T15:02:48Z","abstract_excerpt":"We address the problem of solving strongly convex and smooth minimization problems using stochastic gradient descent (SGD) algorithm with a constant step size. Previous works suggested to combine the Polyak-Ruppert averaging procedure with the Richardson-Romberg extrapolation to reduce the asymptotic bias of SGD at the expense of a mild increase of the variance. We significantly extend previous results by providing an expansion of the mean-squared error of the resulting estimator with respect to the number of iterations $n$. We show that the root mean-squared error can be decomposed into the s"},"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":"2410.05106","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-10-07T15:02:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"07c1d377ac52515bec83b965e9f863b5520156ab7ad87b1ff6ecec76eb315f85","abstract_canon_sha256":"7666768d17ceb169c132bf347fe84ecac5af7f3a26f902e8896885bd9a8af578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:20.414498Z","signature_b64":"Bd7NpQ4d7BwLWc7+tHINSfIl3iMnaUHCcscd1gu6GxftyTUYaGnFp72/8GO1IB2lkUJ/3hOfGG3ae2b0pljhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303f3a3a0a48f7a4f311746f00017122eddf295bb032e96c8e631186c0ec3b28","last_reissued_at":"2026-07-05T11:50:20.414023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:20.414023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alain Durmus, Alexey Naumov, Denis Belomestny, Eric Moulines, Marina Sheshukova, Sergey Samsonov","submitted_at":"2024-10-07T15:02:48Z","abstract_excerpt":"We address the problem of solving strongly convex and smooth minimization problems using stochastic gradient descent (SGD) algorithm with a constant step size. Previous works suggested to combine the Polyak-Ruppert averaging procedure with the Richardson-Romberg extrapolation to reduce the asymptotic bias of SGD at the expense of a mild increase of the variance. We significantly extend previous results by providing an expansion of the mean-squared error of the resulting estimator with respect to the number of iterations $n$. We show that the root mean-squared error can be decomposed into the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05106","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.05106/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":"2410.05106","created_at":"2026-07-05T11:50:20.414079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05106v3","created_at":"2026-07-05T11:50:20.414079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05106","created_at":"2026-07-05T11:50:20.414079+00:00"},{"alias_kind":"pith_short_12","alias_value":"GA7TUOQKJD32","created_at":"2026-07-05T11:50:20.414079+00:00"},{"alias_kind":"pith_short_16","alias_value":"GA7TUOQKJD32J4YR","created_at":"2026-07-05T11:50:20.414079+00:00"},{"alias_kind":"pith_short_8","alias_value":"GA7TUOQK","created_at":"2026-07-05T11:50:20.414079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06719","citing_title":"Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10373","citing_title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL","json":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL.json","graph_json":"https://pith.science/api/pith-number/GA7TUOQKJD32J4YRORXQAALREL/graph.json","events_json":"https://pith.science/api/pith-number/GA7TUOQKJD32J4YRORXQAALREL/events.json","paper":"https://pith.science/paper/GA7TUOQK"},"agent_actions":{"view_html":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL","download_json":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL.json","view_paper":"https://pith.science/paper/GA7TUOQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05106&json=true","fetch_graph":"https://pith.science/api/pith-number/GA7TUOQKJD32J4YRORXQAALREL/graph.json","fetch_events":"https://pith.science/api/pith-number/GA7TUOQKJD32J4YRORXQAALREL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL/action/storage_attestation","attest_author":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL/action/author_attestation","sign_citation":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL/action/citation_signature","submit_replication":"https://pith.science/pith/GA7TUOQKJD32J4YRORXQAALREL/action/replication_record"}},"created_at":"2026-07-05T11:50:20.414079+00:00","updated_at":"2026-07-05T11:50:20.414079+00:00"}