{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:INXEZYLKAKTIWOOFYIDKVCEP2X","short_pith_number":"pith:INXEZYLK","schema_version":"1.0","canonical_sha256":"436e4ce16a02a68b39c5c206aa888fd5ded9eedb63a24b58ccc8462fc03a2c15","source":{"kind":"arxiv","id":"2212.01259","version":1},"attestation_state":"computed","paper":{"title":"Covariance Estimators for the ROOT-SGD Algorithm in Online Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoming Huo, Yajun Mei, Yiling Luo","submitted_at":"2022-12-02T15:55:52Z","abstract_excerpt":"Online learning naturally arises in many statistical and machine learning problems. The most widely used methods in online learning are stochastic first-order algorithms. Among this family of algorithms, there is a recently developed algorithm, Recursive One-Over-T SGD (ROOT-SGD). ROOT-SGD is advantageous in that it converges at a non-asymptotically fast rate, and its estimator further converges to a normal distribution. However, this normal distribution has unknown asymptotic covariance; thus cannot be directly applied to measure the uncertainty. To fill this gap, we develop two estimators fo"},"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":"2212.01259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-02T15:55:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f51bc01322cbcf18489dde805ff2f2f480d777dba64747c3a07a748ae13d5159","abstract_canon_sha256":"74d0e972e785f43d4ced451d092bbd260cbcd94304b680a0a9920bb33c92bb90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:51.102818Z","signature_b64":"7lwUagi4eGB6uKPmimdcigXvVBvXMgsmfCJc8ZmAkbk2SAIFptBw2AkjqeDwzK9ICFY8+TXgH5vNAI1fl9JbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436e4ce16a02a68b39c5c206aa888fd5ded9eedb63a24b58ccc8462fc03a2c15","last_reissued_at":"2026-07-05T05:21:51.102406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:51.102406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Covariance Estimators for the ROOT-SGD Algorithm in Online Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoming Huo, Yajun Mei, Yiling Luo","submitted_at":"2022-12-02T15:55:52Z","abstract_excerpt":"Online learning naturally arises in many statistical and machine learning problems. The most widely used methods in online learning are stochastic first-order algorithms. Among this family of algorithms, there is a recently developed algorithm, Recursive One-Over-T SGD (ROOT-SGD). ROOT-SGD is advantageous in that it converges at a non-asymptotically fast rate, and its estimator further converges to a normal distribution. However, this normal distribution has unknown asymptotic covariance; thus cannot be directly applied to measure the uncertainty. To fill this gap, we develop two estimators fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01259","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/2212.01259/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":"2212.01259","created_at":"2026-07-05T05:21:51.102461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01259v1","created_at":"2026-07-05T05:21:51.102461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01259","created_at":"2026-07-05T05:21:51.102461+00:00"},{"alias_kind":"pith_short_12","alias_value":"INXEZYLKAKTI","created_at":"2026-07-05T05:21:51.102461+00:00"},{"alias_kind":"pith_short_16","alias_value":"INXEZYLKAKTIWOOF","created_at":"2026-07-05T05:21:51.102461+00:00"},{"alias_kind":"pith_short_8","alias_value":"INXEZYLK","created_at":"2026-07-05T05:21:51.102461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.07114","citing_title":"Online Covariance Matrix Estimation in Sketched Newton Methods","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21203","citing_title":"Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10814","citing_title":"Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X","json":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X.json","graph_json":"https://pith.science/api/pith-number/INXEZYLKAKTIWOOFYIDKVCEP2X/graph.json","events_json":"https://pith.science/api/pith-number/INXEZYLKAKTIWOOFYIDKVCEP2X/events.json","paper":"https://pith.science/paper/INXEZYLK"},"agent_actions":{"view_html":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X","download_json":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X.json","view_paper":"https://pith.science/paper/INXEZYLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01259&json=true","fetch_graph":"https://pith.science/api/pith-number/INXEZYLKAKTIWOOFYIDKVCEP2X/graph.json","fetch_events":"https://pith.science/api/pith-number/INXEZYLKAKTIWOOFYIDKVCEP2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X/action/storage_attestation","attest_author":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X/action/author_attestation","sign_citation":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X/action/citation_signature","submit_replication":"https://pith.science/pith/INXEZYLKAKTIWOOFYIDKVCEP2X/action/replication_record"}},"created_at":"2026-07-05T05:21:51.102461+00:00","updated_at":"2026-07-05T05:21:51.102461+00:00"}