{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YQCN26ORYA4ZF5WLBUP6ARSUF7","short_pith_number":"pith:YQCN26OR","schema_version":"1.0","canonical_sha256":"c404dd79d1c03992f6cb0d1fe046542fe1f17906ab6e4340596f644e4c2c45d1","source":{"kind":"arxiv","id":"2209.07446","version":1},"attestation_state":"computed","paper":{"title":"Efficiency Ordering of Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Do Young Eun, Jie Hu, Vishwaraj Doshi","submitted_at":"2022-09-15T16:50:55Z","abstract_excerpt":"We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i.i.d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense. Specifically, we employ the notion of `efficiency ordering', a well-analyzed tool for comparing the performance of Markov Chain Monte Carlo (MCMC) samplers, for SGD algorithms in the form of Loewner ordering of covariance matrices associated with the scaled iterate errors in the long term. Using this ordering, we show that input sequences that are more efficient for MCMC sampling a"},"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":"2209.07446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T16:50:55Z","cross_cats_sorted":[],"title_canon_sha256":"0bb82205a061cd20f11cc12a02e552d9752640398b0b08eabadd677e2b9afe59","abstract_canon_sha256":"69bb0b4a826d696221f7a8a5140c9166ee80faf9cf925a2549cc633e5600ee1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:58.768795Z","signature_b64":"K+G0rDsB8KV1Gdr8Sk/3C367tOsjdAICEdGfBk9dfFAUM5EsyLy3QUOfYxyxnd0eRg6CVf2TfLAY03HgGVlKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c404dd79d1c03992f6cb0d1fe046542fe1f17906ab6e4340596f644e4c2c45d1","last_reissued_at":"2026-07-05T04:57:58.768384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:58.768384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiency Ordering of Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Do Young Eun, Jie Hu, Vishwaraj Doshi","submitted_at":"2022-09-15T16:50:55Z","abstract_excerpt":"We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i.i.d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense. Specifically, we employ the notion of `efficiency ordering', a well-analyzed tool for comparing the performance of Markov Chain Monte Carlo (MCMC) samplers, for SGD algorithms in the form of Loewner ordering of covariance matrices associated with the scaled iterate errors in the long term. Using this ordering, we show that input sequences that are more efficient for MCMC sampling a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07446","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/2209.07446/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":"2209.07446","created_at":"2026-07-05T04:57:58.768441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07446v1","created_at":"2026-07-05T04:57:58.768441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07446","created_at":"2026-07-05T04:57:58.768441+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQCN26ORYA4Z","created_at":"2026-07-05T04:57:58.768441+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQCN26ORYA4ZF5WL","created_at":"2026-07-05T04:57:58.768441+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQCN26OR","created_at":"2026-07-05T04:57:58.768441+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/YQCN26ORYA4ZF5WLBUP6ARSUF7","json":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7.json","graph_json":"https://pith.science/api/pith-number/YQCN26ORYA4ZF5WLBUP6ARSUF7/graph.json","events_json":"https://pith.science/api/pith-number/YQCN26ORYA4ZF5WLBUP6ARSUF7/events.json","paper":"https://pith.science/paper/YQCN26OR"},"agent_actions":{"view_html":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7","download_json":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7.json","view_paper":"https://pith.science/paper/YQCN26OR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07446&json=true","fetch_graph":"https://pith.science/api/pith-number/YQCN26ORYA4ZF5WLBUP6ARSUF7/graph.json","fetch_events":"https://pith.science/api/pith-number/YQCN26ORYA4ZF5WLBUP6ARSUF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7/action/storage_attestation","attest_author":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7/action/author_attestation","sign_citation":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7/action/citation_signature","submit_replication":"https://pith.science/pith/YQCN26ORYA4ZF5WLBUP6ARSUF7/action/replication_record"}},"created_at":"2026-07-05T04:57:58.768441+00:00","updated_at":"2026-07-05T04:57:58.768441+00:00"}