{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GGFRGXWXDBAT354LVGYGXQLTPB","short_pith_number":"pith:GGFRGXWX","schema_version":"1.0","canonical_sha256":"318b135ed718413df78ba9b06bc1737846e5a5e7b561007f69e31d3baf3e0e24","source":{"kind":"arxiv","id":"2206.02275","version":1},"attestation_state":"computed","paper":{"title":"Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tyurin, Konstantin Burlachenko, Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-06-05T21:32:33Z","abstract_excerpt":"We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient evaluations of individual functions is $\\mathcal{O}\\left(n + n^{1/2}\\varepsilon^{-1}\\right)$, attained by the optimal SGD methods $\\small\\sf\\color{green}{SPIDER}$(arXiv:1807.01695) and $\\small\\sf\\color{green}{PAGE}$(arXiv:2008.10898), for example, where $\\varepsilon$ is the error tolerance. However, i) the big-$\\mathcal{O}$ notation hides crucial dependencies on th"},"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":"2206.02275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-05T21:32:33Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cd64b0521f35d33b586da78729c5d2d50110ea7f364b42bb66b5de1ddbf5c15b","abstract_canon_sha256":"049c68c78f9b6f85264a1b6b400f22b164091a02184cbc46f72e92783f53d43e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:16.017122Z","signature_b64":"YEEUr2Zv6lRVwqNtvRtbjLs2b1kEEVf7hz9oln+7i1CTPZzAwsx3qVMJ4UUdkZWpeW5re9vNTywAHMRc9wTTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318b135ed718413df78ba9b06bc1737846e5a5e7b561007f69e31d3baf3e0e24","last_reissued_at":"2026-07-05T04:29:16.016712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:16.016712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tyurin, Konstantin Burlachenko, Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-06-05T21:32:33Z","abstract_excerpt":"We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient evaluations of individual functions is $\\mathcal{O}\\left(n + n^{1/2}\\varepsilon^{-1}\\right)$, attained by the optimal SGD methods $\\small\\sf\\color{green}{SPIDER}$(arXiv:1807.01695) and $\\small\\sf\\color{green}{PAGE}$(arXiv:2008.10898), for example, where $\\varepsilon$ is the error tolerance. However, i) the big-$\\mathcal{O}$ notation hides crucial dependencies on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02275","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/2206.02275/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":"2206.02275","created_at":"2026-07-05T04:29:16.016768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02275v1","created_at":"2026-07-05T04:29:16.016768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02275","created_at":"2026-07-05T04:29:16.016768+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGFRGXWXDBAT","created_at":"2026-07-05T04:29:16.016768+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGFRGXWXDBAT354L","created_at":"2026-07-05T04:29:16.016768+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGFRGXWX","created_at":"2026-07-05T04:29:16.016768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.15368","citing_title":"Tighter Performance Theory of FedExProx","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB","json":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB.json","graph_json":"https://pith.science/api/pith-number/GGFRGXWXDBAT354LVGYGXQLTPB/graph.json","events_json":"https://pith.science/api/pith-number/GGFRGXWXDBAT354LVGYGXQLTPB/events.json","paper":"https://pith.science/paper/GGFRGXWX"},"agent_actions":{"view_html":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB","download_json":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB.json","view_paper":"https://pith.science/paper/GGFRGXWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02275&json=true","fetch_graph":"https://pith.science/api/pith-number/GGFRGXWXDBAT354LVGYGXQLTPB/graph.json","fetch_events":"https://pith.science/api/pith-number/GGFRGXWXDBAT354LVGYGXQLTPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB/action/storage_attestation","attest_author":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB/action/author_attestation","sign_citation":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB/action/citation_signature","submit_replication":"https://pith.science/pith/GGFRGXWXDBAT354LVGYGXQLTPB/action/replication_record"}},"created_at":"2026-07-05T04:29:16.016768+00:00","updated_at":"2026-07-05T04:29:16.016768+00:00"}