{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F66G75C2S47X7TVQMY5YDAN5BC","short_pith_number":"pith:F66G75C2","schema_version":"1.0","canonical_sha256":"2fbc6ff45a973f7fceb0663b8181bd089706abb76b0ce13b860ccda45f824820","source":{"kind":"arxiv","id":"2407.02322","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Adrien Schertzer, Loucas Pillaud-Vivien","submitted_at":"2024-07-02T14:52:21Z","abstract_excerpt":"We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either in the case of the training loss (finite samples) or the population one (online setting). A key qualitative feature of the dynamics is the existence of a perfect interpolator of the data, irrespective of the sample size. In both scenarios, we provide precise, non-asymptotic rates of convergence to the (possibly degenerate) stationary distribution. Additiona"},"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":"2407.02322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T14:52:21Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"8c6c742577a57c9f62b013505d4b6e421a4566c9e97be96f2139fb37da2825b3","abstract_canon_sha256":"523f45ec29b15ea182f1e66bbcefd0f2fa0bbe4cefe32b960e26e71e592aa156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:22.657878Z","signature_b64":"H0n1uSJ1y6FadvK0jXbCEjG2jAJ8iiLk1Qz+YRb1V5edCYgrz6z9shrTzsrSKlY+gZAA7Z9VzYbmrbAnRAXZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fbc6ff45a973f7fceb0663b8181bd089706abb76b0ce13b860ccda45f824820","last_reissued_at":"2026-07-05T08:39:22.657403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:22.657403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Adrien Schertzer, Loucas Pillaud-Vivien","submitted_at":"2024-07-02T14:52:21Z","abstract_excerpt":"We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either in the case of the training loss (finite samples) or the population one (online setting). A key qualitative feature of the dynamics is the existence of a perfect interpolator of the data, irrespective of the sample size. In both scenarios, we provide precise, non-asymptotic rates of convergence to the (possibly degenerate) stationary distribution. Additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02322","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/2407.02322/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":"2407.02322","created_at":"2026-07-05T08:39:22.657463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02322v1","created_at":"2026-07-05T08:39:22.657463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02322","created_at":"2026-07-05T08:39:22.657463+00:00"},{"alias_kind":"pith_short_12","alias_value":"F66G75C2S47X","created_at":"2026-07-05T08:39:22.657463+00:00"},{"alias_kind":"pith_short_16","alias_value":"F66G75C2S47X7TVQ","created_at":"2026-07-05T08:39:22.657463+00:00"},{"alias_kind":"pith_short_8","alias_value":"F66G75C2","created_at":"2026-07-05T08:39:22.657463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26000","citing_title":"Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC","json":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC.json","graph_json":"https://pith.science/api/pith-number/F66G75C2S47X7TVQMY5YDAN5BC/graph.json","events_json":"https://pith.science/api/pith-number/F66G75C2S47X7TVQMY5YDAN5BC/events.json","paper":"https://pith.science/paper/F66G75C2"},"agent_actions":{"view_html":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC","download_json":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC.json","view_paper":"https://pith.science/paper/F66G75C2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02322&json=true","fetch_graph":"https://pith.science/api/pith-number/F66G75C2S47X7TVQMY5YDAN5BC/graph.json","fetch_events":"https://pith.science/api/pith-number/F66G75C2S47X7TVQMY5YDAN5BC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC/action/storage_attestation","attest_author":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC/action/author_attestation","sign_citation":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC/action/citation_signature","submit_replication":"https://pith.science/pith/F66G75C2S47X7TVQMY5YDAN5BC/action/replication_record"}},"created_at":"2026-07-05T08:39:22.657463+00:00","updated_at":"2026-07-05T08:39:22.657463+00:00"}