{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RKO7TYWS7RZTEB3BKS7BLSUNBJ","short_pith_number":"pith:RKO7TYWS","schema_version":"1.0","canonical_sha256":"8a9df9e2d2fc7332076154be15ca8d0a406789a55995dd81a0471f7034dd9eed","source":{"kind":"arxiv","id":"2307.06915","version":3},"attestation_state":"computed","paper":{"title":"Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Wanrong Zhu, Wei Biao Wu, Ziyang Wei","submitted_at":"2023-07-13T17:29:01Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in different settings. In this paper, we explore a general averaging scheme for SGD. Specifically, we establish the asymptotic normality of a broad range of weighted averaged SGD solutions and provide asymptotically valid online inference approaches. Furthermore, we propose an adaptive averaging scheme that exhibits both optimal statistical rate and favorable "},"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":"2307.06915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-07-13T17:29:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f13742d55541dc887ba8bce096f8abb82802012026938da5270c5d5daa23022b","abstract_canon_sha256":"3af885fe2800ec361ee8df22940592e175df0e2a355c55d6bb61080a5f19a258"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:03.792809Z","signature_b64":"VYNdwwblSF+R5LQ5M+PdcUCRAMn05G1fNB7GNbh9UL8o9wa+mzLIz2Eq8Pkzny2wPNuiTSnzWo4fGS/mU6pECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a9df9e2d2fc7332076154be15ca8d0a406789a55995dd81a0471f7034dd9eed","last_reissued_at":"2026-07-05T10:45:03.792207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:03.792207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Wanrong Zhu, Wei Biao Wu, Ziyang Wei","submitted_at":"2023-07-13T17:29:01Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in different settings. In this paper, we explore a general averaging scheme for SGD. Specifically, we establish the asymptotic normality of a broad range of weighted averaged SGD solutions and provide asymptotically valid online inference approaches. Furthermore, we propose an adaptive averaging scheme that exhibits both optimal statistical rate and favorable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06915","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/2307.06915/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":"2307.06915","created_at":"2026-07-05T10:45:03.792269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06915v3","created_at":"2026-07-05T10:45:03.792269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06915","created_at":"2026-07-05T10:45:03.792269+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKO7TYWS7RZT","created_at":"2026-07-05T10:45:03.792269+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKO7TYWS7RZTEB3B","created_at":"2026-07-05T10:45:03.792269+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKO7TYWS","created_at":"2026-07-05T10:45:03.792269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17364","citing_title":"A Polyak-Ruppert Central Limit Theorem for SA-Adam with Momentum and Non-Convergent Adaptive Preconditioning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19291","citing_title":"Factor Augmented High-Dimensional SGD","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23498","citing_title":"When Does Dynamic Preconditioning Preserve the Polyak-Ruppert CLT? A Stabilization Threshold","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ","json":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ.json","graph_json":"https://pith.science/api/pith-number/RKO7TYWS7RZTEB3BKS7BLSUNBJ/graph.json","events_json":"https://pith.science/api/pith-number/RKO7TYWS7RZTEB3BKS7BLSUNBJ/events.json","paper":"https://pith.science/paper/RKO7TYWS"},"agent_actions":{"view_html":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ","download_json":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ.json","view_paper":"https://pith.science/paper/RKO7TYWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06915&json=true","fetch_graph":"https://pith.science/api/pith-number/RKO7TYWS7RZTEB3BKS7BLSUNBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RKO7TYWS7RZTEB3BKS7BLSUNBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ/action/storage_attestation","attest_author":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ/action/author_attestation","sign_citation":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ/action/citation_signature","submit_replication":"https://pith.science/pith/RKO7TYWS7RZTEB3BKS7BLSUNBJ/action/replication_record"}},"created_at":"2026-07-05T10:45:03.792269+00:00","updated_at":"2026-07-05T10:45:03.792269+00:00"}