{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SZAUBTQVDB4UDRQS7QMBW3X5CW","short_pith_number":"pith:SZAUBTQV","schema_version":"1.0","canonical_sha256":"964140ce15187941c612fc181b6efd158d77bf7b2f131733a036df939fe85be4","source":{"kind":"arxiv","id":"1905.11266","version":2},"attestation_state":"computed","paper":{"title":"One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Filip Hanzely, Peter Richt\\'arik","submitted_at":"2019-05-27T14:31:44Z","abstract_excerpt":"We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a large model dimension, or both. In special cases, our method reduces to several known and previously thought to be unrelated methods, such as {\\tt SAGA}, {\\tt LSVRG}, {\\tt JacSketch}, {\\tt SEGA} and {\\tt ISEGA}, and their arbitrary sampling and proximal generalizations. However, we also highlight a large number of new specific algorithms with interesting properties. We provide a single theorem establishing linear con"},"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":"1905.11266","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-05-27T14:31:44Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"48ca167463a88dce2c77e3783e8acf40ad327d61845c0f8823a8cdae05bbceef","abstract_canon_sha256":"02716e33e34ca0bce148c7b6e07f89d81e5416689558ef55961bc3d48e2b7dca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T20:14:33.304026Z","signature_b64":"3MPdPhQyROAqGE1GsyjPgLfzcNOG2wnpBHPi/kejYK/o36VkRXNJerHzfTlSjIJd6ReIyxiqkcXGlN/EGV1jBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"964140ce15187941c612fc181b6efd158d77bf7b2f131733a036df939fe85be4","last_reissued_at":"2026-06-04T20:14:33.303547Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T20:14:33.303547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Filip Hanzely, Peter Richt\\'arik","submitted_at":"2019-05-27T14:31:44Z","abstract_excerpt":"We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a large model dimension, or both. In special cases, our method reduces to several known and previously thought to be unrelated methods, such as {\\tt SAGA}, {\\tt LSVRG}, {\\tt JacSketch}, {\\tt SEGA} and {\\tt ISEGA}, and their arbitrary sampling and proximal generalizations. However, we also highlight a large number of new specific algorithms with interesting properties. We provide a single theorem establishing linear con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11266","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/1905.11266/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":"1905.11266","created_at":"2026-06-04T20:14:33.303609+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11266v2","created_at":"2026-06-04T20:14:33.303609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11266","created_at":"2026-06-04T20:14:33.303609+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZAUBTQVDB4U","created_at":"2026-06-04T20:14:33.303609+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZAUBTQVDB4UDRQS","created_at":"2026-06-04T20:14:33.303609+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZAUBTQV","created_at":"2026-06-04T20:14:33.303609+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/SZAUBTQVDB4UDRQS7QMBW3X5CW","json":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW.json","graph_json":"https://pith.science/api/pith-number/SZAUBTQVDB4UDRQS7QMBW3X5CW/graph.json","events_json":"https://pith.science/api/pith-number/SZAUBTQVDB4UDRQS7QMBW3X5CW/events.json","paper":"https://pith.science/paper/SZAUBTQV"},"agent_actions":{"view_html":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW","download_json":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW.json","view_paper":"https://pith.science/paper/SZAUBTQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11266&json=true","fetch_graph":"https://pith.science/api/pith-number/SZAUBTQVDB4UDRQS7QMBW3X5CW/graph.json","fetch_events":"https://pith.science/api/pith-number/SZAUBTQVDB4UDRQS7QMBW3X5CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW/action/storage_attestation","attest_author":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW/action/author_attestation","sign_citation":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW/action/citation_signature","submit_replication":"https://pith.science/pith/SZAUBTQVDB4UDRQS7QMBW3X5CW/action/replication_record"}},"created_at":"2026-06-04T20:14:33.303609+00:00","updated_at":"2026-06-04T20:14:33.303609+00:00"}