{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y2ZMP2JJLPYNXGPSPMUKI2P5LM","short_pith_number":"pith:Y2ZMP2JJ","schema_version":"1.0","canonical_sha256":"c6b2c7e9295bf0db99f27b28a469fd5b2429eb83874f40df691870b6337ad82a","source":{"kind":"arxiv","id":"1805.02632","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Francis Bach, Peter Richt\\'arik, Robert M. Gower","submitted_at":"2018-05-07T17:38:02Z","abstract_excerpt":"We develop a new family of variance reduced stochastic gradient descent methods for minimizing the average of a very large number of smooth functions. Our method --JacSketch-- is motivated by novel developments in randomized numerical linear algebra, and operates by maintaining a stochastic estimate of a Jacobian matrix composed of the gradients of individual functions. In each iteration, JacSketch efficiently updates the Jacobian matrix by first obtaining a random linear measurement of the true Jacobian through (cheap) sketching, and then projecting the previous estimate onto the solution spa"},"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":"1805.02632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-07T17:38:02Z","cross_cats_sorted":[],"title_canon_sha256":"494be4a12eebfc83ad8df415e987cc4e45ebc0ff659baa2775fd84e19cb98528","abstract_canon_sha256":"2f8feca85753dd981910ff2e1879bc72eb8f5c119d1044ade71dfbb50cc415e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:39.452962Z","signature_b64":"daOuNT0PpD/V77LkcLlLezdap0TWeD4MBgRHQRwyO74ruVx88jU/HwZfC3mNVaEKixtUtotzrvItmcSt+cGsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b2c7e9295bf0db99f27b28a469fd5b2429eb83874f40df691870b6337ad82a","last_reissued_at":"2026-05-18T00:16:39.452404Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:39.452404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Francis Bach, Peter Richt\\'arik, Robert M. Gower","submitted_at":"2018-05-07T17:38:02Z","abstract_excerpt":"We develop a new family of variance reduced stochastic gradient descent methods for minimizing the average of a very large number of smooth functions. Our method --JacSketch-- is motivated by novel developments in randomized numerical linear algebra, and operates by maintaining a stochastic estimate of a Jacobian matrix composed of the gradients of individual functions. In each iteration, JacSketch efficiently updates the Jacobian matrix by first obtaining a random linear measurement of the true Jacobian through (cheap) sketching, and then projecting the previous estimate onto the solution spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02632","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":""},"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":"1805.02632","created_at":"2026-05-18T00:16:39.452517+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.02632v1","created_at":"2026-05-18T00:16:39.452517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02632","created_at":"2026-05-18T00:16:39.452517+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2ZMP2JJLPYN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2ZMP2JJLPYNXGPS","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2ZMP2JJ","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08871","citing_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","ref_index":279,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM","json":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM.json","graph_json":"https://pith.science/api/pith-number/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/graph.json","events_json":"https://pith.science/api/pith-number/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/events.json","paper":"https://pith.science/paper/Y2ZMP2JJ"},"agent_actions":{"view_html":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM","download_json":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM.json","view_paper":"https://pith.science/paper/Y2ZMP2JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.02632&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/action/storage_attestation","attest_author":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/action/author_attestation","sign_citation":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/action/citation_signature","submit_replication":"https://pith.science/pith/Y2ZMP2JJLPYNXGPSPMUKI2P5LM/action/replication_record"}},"created_at":"2026-05-18T00:16:39.452517+00:00","updated_at":"2026-05-18T00:16:39.452517+00:00"}