{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OBQMTU4BXF7V6WSDBFL5TBDNAX","short_pith_number":"pith:OBQMTU4B","schema_version":"1.0","canonical_sha256":"7060c9d381b97f5f5a430957d9846d05eb00696fe748fc204f539a3d4b0eb904","source":{"kind":"arxiv","id":"2106.14588","version":1},"attestation_state":"computed","paper":{"title":"The Convergence Rate of SGD's Final Iterate: Analysis on Dimension Dependence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Daogao Liu, Zhou Lu","submitted_at":"2021-06-28T11:51:04Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is among the simplest and most popular methods in optimization. The convergence rate for SGD has been extensively studied and tight analyses have been established for the running average scheme, but the sub-optimality of the final iterate is still not well-understood. shamir2013stochastic gave the best known upper bound for the final iterate of SGD minimizing non-smooth convex functions, which is $O(\\log T/\\sqrt{T})$ for Lipschitz convex functions and $O(\\log T/ T)$ with additional assumption on strongly convexity. The best known lower bounds, however, are wor"},"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":"2106.14588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-06-28T11:51:04Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4390ca00b405260df8e626ae9ffbc9519990d53150ac4ef320af45dcceec9509","abstract_canon_sha256":"3d0c4a5a13e02f5b593b09efe42a20b0a2c15c953607e08b105c5650f4830605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:51.934805Z","signature_b64":"jo1Wzuz+BHH46TfKT0PS+sK1lZFZQNiODMGMbaPNdTjYOhFPUXGLDXZzhkiMiAqYe5QgwjbfzrZTNULgtWhpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7060c9d381b97f5f5a430957d9846d05eb00696fe748fc204f539a3d4b0eb904","last_reissued_at":"2026-07-05T02:52:51.934392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:51.934392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Convergence Rate of SGD's Final Iterate: Analysis on Dimension Dependence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Daogao Liu, Zhou Lu","submitted_at":"2021-06-28T11:51:04Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is among the simplest and most popular methods in optimization. The convergence rate for SGD has been extensively studied and tight analyses have been established for the running average scheme, but the sub-optimality of the final iterate is still not well-understood. shamir2013stochastic gave the best known upper bound for the final iterate of SGD minimizing non-smooth convex functions, which is $O(\\log T/\\sqrt{T})$ for Lipschitz convex functions and $O(\\log T/ T)$ with additional assumption on strongly convexity. The best known lower bounds, however, are wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14588","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/2106.14588/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":"2106.14588","created_at":"2026-07-05T02:52:51.934450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14588v1","created_at":"2026-07-05T02:52:51.934450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14588","created_at":"2026-07-05T02:52:51.934450+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBQMTU4BXF7V","created_at":"2026-07-05T02:52:51.934450+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBQMTU4BXF7V6WSD","created_at":"2026-07-05T02:52:51.934450+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBQMTU4B","created_at":"2026-07-05T02:52:51.934450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24879","citing_title":"New Bounds for the Last Iterate of the Stochastic subGradient Method","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX","json":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX.json","graph_json":"https://pith.science/api/pith-number/OBQMTU4BXF7V6WSDBFL5TBDNAX/graph.json","events_json":"https://pith.science/api/pith-number/OBQMTU4BXF7V6WSDBFL5TBDNAX/events.json","paper":"https://pith.science/paper/OBQMTU4B"},"agent_actions":{"view_html":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX","download_json":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX.json","view_paper":"https://pith.science/paper/OBQMTU4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14588&json=true","fetch_graph":"https://pith.science/api/pith-number/OBQMTU4BXF7V6WSDBFL5TBDNAX/graph.json","fetch_events":"https://pith.science/api/pith-number/OBQMTU4BXF7V6WSDBFL5TBDNAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX/action/storage_attestation","attest_author":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX/action/author_attestation","sign_citation":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX/action/citation_signature","submit_replication":"https://pith.science/pith/OBQMTU4BXF7V6WSDBFL5TBDNAX/action/replication_record"}},"created_at":"2026-07-05T02:52:51.934450+00:00","updated_at":"2026-07-05T02:52:51.934450+00:00"}