{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KJB5YHCCI73C4AP6PHLT7DIZCO","short_pith_number":"pith:KJB5YHCC","schema_version":"1.0","canonical_sha256":"5243dc1c4247f62e01fe79d73f8d19139290e8a4fbe983c728512bb2700e3871","source":{"kind":"arxiv","id":"2311.14222","version":1},"attestation_state":"computed","paper":{"title":"Risk Bounds of Accelerated SGD for Overparameterized Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jingfeng Wu, Quanquan Gu, Xuheng Li, Yihe Deng","submitted_at":"2023-11-23T23:02:10Z","abstract_excerpt":"Accelerated stochastic gradient descent (ASGD) is a workhorse in deep learning and often achieves better generalization performance than SGD. However, existing optimization theory can only explain the faster convergence of ASGD, but cannot explain its better generalization. In this paper, we study the generalization of ASGD for overparameterized linear regression, which is possibly the simplest setting of learning with overparameterization. We establish an instance-dependent excess risk bound for ASGD within each eigen-subspace of the data covariance matrix. Our analysis shows that (i) ASGD ou"},"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":"2311.14222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T23:02:10Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c873b7e2cdd5f269e49b37d1806d2ad0e1c765049e9ebec2dc4080230fe5a1dd","abstract_canon_sha256":"d7a952614bdd9d9ce2155c7d6dd358b95d5f1389b69d7473bcc562b9b734bce1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:14.918005Z","signature_b64":"52N+HJf/yH2a9nAW5sw7Nws5MhogzZvADgyVPTEmEagXvH34kCWJK08nullI+PfPRzu8emoDDhCRR5YReMF8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5243dc1c4247f62e01fe79d73f8d19139290e8a4fbe983c728512bb2700e3871","last_reissued_at":"2026-07-05T07:16:14.917486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:14.917486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk Bounds of Accelerated SGD for Overparameterized Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jingfeng Wu, Quanquan Gu, Xuheng Li, Yihe Deng","submitted_at":"2023-11-23T23:02:10Z","abstract_excerpt":"Accelerated stochastic gradient descent (ASGD) is a workhorse in deep learning and often achieves better generalization performance than SGD. However, existing optimization theory can only explain the faster convergence of ASGD, but cannot explain its better generalization. In this paper, we study the generalization of ASGD for overparameterized linear regression, which is possibly the simplest setting of learning with overparameterization. We establish an instance-dependent excess risk bound for ASGD within each eigen-subspace of the data covariance matrix. Our analysis shows that (i) ASGD ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14222","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/2311.14222/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":"2311.14222","created_at":"2026-07-05T07:16:14.917536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14222v1","created_at":"2026-07-05T07:16:14.917536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14222","created_at":"2026-07-05T07:16:14.917536+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJB5YHCCI73C","created_at":"2026-07-05T07:16:14.917536+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJB5YHCCI73C4AP6","created_at":"2026-07-05T07:16:14.917536+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJB5YHCC","created_at":"2026-07-05T07:16:14.917536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16098","citing_title":"Dimension-adapted Momentum Outscales SGD","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO","json":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO.json","graph_json":"https://pith.science/api/pith-number/KJB5YHCCI73C4AP6PHLT7DIZCO/graph.json","events_json":"https://pith.science/api/pith-number/KJB5YHCCI73C4AP6PHLT7DIZCO/events.json","paper":"https://pith.science/paper/KJB5YHCC"},"agent_actions":{"view_html":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO","download_json":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO.json","view_paper":"https://pith.science/paper/KJB5YHCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14222&json=true","fetch_graph":"https://pith.science/api/pith-number/KJB5YHCCI73C4AP6PHLT7DIZCO/graph.json","fetch_events":"https://pith.science/api/pith-number/KJB5YHCCI73C4AP6PHLT7DIZCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO/action/storage_attestation","attest_author":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO/action/author_attestation","sign_citation":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO/action/citation_signature","submit_replication":"https://pith.science/pith/KJB5YHCCI73C4AP6PHLT7DIZCO/action/replication_record"}},"created_at":"2026-07-05T07:16:14.917536+00:00","updated_at":"2026-07-05T07:16:14.917536+00:00"}