{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7TVDGN6YN2L25BRD55H7ZEYPFA","short_pith_number":"pith:7TVDGN6Y","schema_version":"1.0","canonical_sha256":"fcea3337d86e97ae8623ef4ffc930f28083280ef6f35bba89e0026d98bfad566","source":{"kind":"arxiv","id":"1809.03054","version":2},"attestation_state":"computed","paper":{"title":"SEGA: Variance Reduction via Gradient Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Filip Hanzely, Konstantin Mishchenko, Peter Richtarik","submitted_at":"2018-09-09T22:40:52Z","abstract_excerpt":"We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the gradient obtained from an oracle. In each iteration, SEGA updates the current estimate of the gradient through a sketch-and-project operation using the information provided by the latest sketch, and this is subsequently used to compute an unbiased estimate of the true gradient through a random relaxation procedure. This unbiased estimate is then used to perfor"},"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":"1809.03054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-09T22:40:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5028af37ddda7d185540eef8d11bfb839bec3356b51696d98e2dbcbcd1080e2e","abstract_canon_sha256":"b74394d7ea02761796775f8c060f4d391a0b7a2d494109ac19bf94e0b195bdd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:54.629682Z","signature_b64":"q9LAb6Mou0grgNlFhriV9N+kuXkF6aXD/EQ0mY1GgQVS53JBjVHFkz2Z1GmaqWeBI4OK3qZxhk3yVawiivFeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcea3337d86e97ae8623ef4ffc930f28083280ef6f35bba89e0026d98bfad566","last_reissued_at":"2026-05-18T00:02:54.628985Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:54.628985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEGA: Variance Reduction via Gradient Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Filip Hanzely, Konstantin Mishchenko, Peter Richtarik","submitted_at":"2018-09-09T22:40:52Z","abstract_excerpt":"We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the gradient obtained from an oracle. In each iteration, SEGA updates the current estimate of the gradient through a sketch-and-project operation using the information provided by the latest sketch, and this is subsequently used to compute an unbiased estimate of the true gradient through a random relaxation procedure. This unbiased estimate is then used to perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03054","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":""},"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":"1809.03054","created_at":"2026-05-18T00:02:54.629092+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03054v2","created_at":"2026-05-18T00:02:54.629092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03054","created_at":"2026-05-18T00:02:54.629092+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TVDGN6YN2L2","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TVDGN6YN2L25BRD","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TVDGN6Y","created_at":"2026-05-18T12:32:11.075285+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/7TVDGN6YN2L25BRD55H7ZEYPFA","json":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA.json","graph_json":"https://pith.science/api/pith-number/7TVDGN6YN2L25BRD55H7ZEYPFA/graph.json","events_json":"https://pith.science/api/pith-number/7TVDGN6YN2L25BRD55H7ZEYPFA/events.json","paper":"https://pith.science/paper/7TVDGN6Y"},"agent_actions":{"view_html":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA","download_json":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA.json","view_paper":"https://pith.science/paper/7TVDGN6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03054&json=true","fetch_graph":"https://pith.science/api/pith-number/7TVDGN6YN2L25BRD55H7ZEYPFA/graph.json","fetch_events":"https://pith.science/api/pith-number/7TVDGN6YN2L25BRD55H7ZEYPFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA/action/storage_attestation","attest_author":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA/action/author_attestation","sign_citation":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA/action/citation_signature","submit_replication":"https://pith.science/pith/7TVDGN6YN2L25BRD55H7ZEYPFA/action/replication_record"}},"created_at":"2026-05-18T00:02:54.629092+00:00","updated_at":"2026-05-18T00:02:54.629092+00:00"}