{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HUVANSSJTQWXEKSEYHDYVU5SAO","short_pith_number":"pith:HUVANSSJ","schema_version":"1.0","canonical_sha256":"3d2a06ca499c2d722a44c1c78ad3b203b5e721326b1782998334b1366f0fafa0","source":{"kind":"arxiv","id":"2102.09718","version":2},"attestation_state":"computed","paper":{"title":"Permutation-Based SGD: Is Random Optimal?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Kangwook Lee, Shashank Rajput","submitted_at":"2021-02-19T03:14:28Z","abstract_excerpt":"A recent line of ground-breaking results for permutation-based SGD has corroborated a widely observed phenomenon: random permutations offer faster convergence than with-replacement sampling. However, is random optimal? We show that this depends heavily on what functions we are optimizing, and the convergence gap between optimal and random permutations can vary from exponential to nonexistent. We first show that for 1-dimensional strongly convex functions, with smooth second derivatives, there exist permutations that offer exponentially faster convergence compared to random. However, for genera"},"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":"2102.09718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T03:14:28Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"b9c9cf0013684d2d639094660d114ff4fe5b852fe9c17e3233ea7210a7128763","abstract_canon_sha256":"701bc3e0ab46b9d8f9e37ba3f3375c077b4b268d15a2fc694c43758a70c7f06c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:56.336391Z","signature_b64":"HC/6Zf+7ER/8FJ4iO0wcxxqbjEbNxdiFdKs3Wo1kPtFe2CHHTDywrdOoGA3sIBJGsYj8/ncuWJukLu7rJ/gDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2a06ca499c2d722a44c1c78ad3b203b5e721326b1782998334b1366f0fafa0","last_reissued_at":"2026-07-05T03:34:56.335014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:56.335014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Permutation-Based SGD: Is Random Optimal?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Kangwook Lee, Shashank Rajput","submitted_at":"2021-02-19T03:14:28Z","abstract_excerpt":"A recent line of ground-breaking results for permutation-based SGD has corroborated a widely observed phenomenon: random permutations offer faster convergence than with-replacement sampling. However, is random optimal? We show that this depends heavily on what functions we are optimizing, and the convergence gap between optimal and random permutations can vary from exponential to nonexistent. We first show that for 1-dimensional strongly convex functions, with smooth second derivatives, there exist permutations that offer exponentially faster convergence compared to random. However, for genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09718","kind":"arxiv","version":2},"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/2102.09718/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":"2102.09718","created_at":"2026-07-05T03:34:56.335980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09718v2","created_at":"2026-07-05T03:34:56.335980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09718","created_at":"2026-07-05T03:34:56.335980+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUVANSSJTQWX","created_at":"2026-07-05T03:34:56.335980+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUVANSSJTQWXEKSE","created_at":"2026-07-05T03:34:56.335980+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUVANSSJ","created_at":"2026-07-05T03:34:56.335980+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/HUVANSSJTQWXEKSEYHDYVU5SAO","json":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO.json","graph_json":"https://pith.science/api/pith-number/HUVANSSJTQWXEKSEYHDYVU5SAO/graph.json","events_json":"https://pith.science/api/pith-number/HUVANSSJTQWXEKSEYHDYVU5SAO/events.json","paper":"https://pith.science/paper/HUVANSSJ"},"agent_actions":{"view_html":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO","download_json":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO.json","view_paper":"https://pith.science/paper/HUVANSSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09718&json=true","fetch_graph":"https://pith.science/api/pith-number/HUVANSSJTQWXEKSEYHDYVU5SAO/graph.json","fetch_events":"https://pith.science/api/pith-number/HUVANSSJTQWXEKSEYHDYVU5SAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO/action/storage_attestation","attest_author":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO/action/author_attestation","sign_citation":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO/action/citation_signature","submit_replication":"https://pith.science/pith/HUVANSSJTQWXEKSEYHDYVU5SAO/action/replication_record"}},"created_at":"2026-07-05T03:34:56.335980+00:00","updated_at":"2026-07-05T03:34:56.335980+00:00"}