{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4V6K4GELSM33R5LMRR2WEWDNOQ","short_pith_number":"pith:4V6K4GEL","schema_version":"1.0","canonical_sha256":"e57cae188b9337b8f56c8c7562586d7409e068dcf3c4466b9170dc2ed1b99d44","source":{"kind":"arxiv","id":"1602.05419","version":2},"attestation_state":"computed","paper":{"title":"Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aymeric Dieuleveut (SIERRA, Francis Bach (SIERRA, LIENS), Nicolas Flammarion (LIENS, SIERRA)","submitted_at":"2016-02-17T14:06:34Z","abstract_excerpt":"We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting of initial conditions in O(1/n 2), and in terms of dependence on the noise and dimension d of the problem, as O(d/n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through fin"},"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":"1602.05419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-17T14:06:34Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5ae014b75f3c6323bd1d6ea5c98f705ed0efad2ed44a7e7d63d1b6f02a810c67","abstract_canon_sha256":"b6e00008472b23bb2052dc63a06d5ad4d5265ec77438a970bb6d44d22e30f65b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:06.119030Z","signature_b64":"IoiyBaejmmzZ776bvgkTYIjm3L0BNha8RIOYjJbbyLPMZW6wLbtR6uh+4a9mEwuu69PER455PoY0P/Kw99GtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e57cae188b9337b8f56c8c7562586d7409e068dcf3c4466b9170dc2ed1b99d44","last_reissued_at":"2026-05-18T01:20:06.118502Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:06.118502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aymeric Dieuleveut (SIERRA, Francis Bach (SIERRA, LIENS), Nicolas Flammarion (LIENS, SIERRA)","submitted_at":"2016-02-17T14:06:34Z","abstract_excerpt":"We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting of initial conditions in O(1/n 2), and in terms of dependence on the noise and dimension d of the problem, as O(d/n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05419","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":"1602.05419","created_at":"2026-05-18T01:20:06.118567+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.05419v2","created_at":"2026-05-18T01:20:06.118567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05419","created_at":"2026-05-18T01:20:06.118567+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V6K4GELSM33","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V6K4GELSM33R5LM","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V6K4GEL","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ","json":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ.json","graph_json":"https://pith.science/api/pith-number/4V6K4GELSM33R5LMRR2WEWDNOQ/graph.json","events_json":"https://pith.science/api/pith-number/4V6K4GELSM33R5LMRR2WEWDNOQ/events.json","paper":"https://pith.science/paper/4V6K4GEL"},"agent_actions":{"view_html":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ","download_json":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ.json","view_paper":"https://pith.science/paper/4V6K4GEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.05419&json=true","fetch_graph":"https://pith.science/api/pith-number/4V6K4GELSM33R5LMRR2WEWDNOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4V6K4GELSM33R5LMRR2WEWDNOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ/action/storage_attestation","attest_author":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ/action/author_attestation","sign_citation":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ/action/citation_signature","submit_replication":"https://pith.science/pith/4V6K4GELSM33R5LMRR2WEWDNOQ/action/replication_record"}},"created_at":"2026-05-18T01:20:06.118567+00:00","updated_at":"2026-05-18T01:20:06.118567+00:00"}