{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QW62AQNHFN2JOLTKEI5WMMTNE5","short_pith_number":"pith:QW62AQNH","schema_version":"1.0","canonical_sha256":"85bda041a72b74972e6a223b66326d2743cf87c686dffe1764aa92adc3ec7d09","source":{"kind":"arxiv","id":"1905.11261","version":1},"attestation_state":"computed","paper":{"title":"A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.OC","authors_text":"Eduard Gorbunov, Filip Hanzely, Peter Richt\\'arik","submitted_at":"2019-05-27T14:28:13Z","abstract_excerpt":"In this paper we introduce a unified analysis of a large family of variants of proximal stochastic gradient descent ({\\tt SGD}) which so far have required different intuitions, convergence analyses, have different applications, and which have been developed separately in various communities. We show that our framework includes methods with and without the following tricks, and their combinations: variance reduction, importance sampling, mini-batch sampling, quantization, and coordinate sub-sampling. As a by-product, we obtain the first unified theory of {\\tt SGD} and randomized coordinate desc"},"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":"1905.11261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-05-27T14:28:13Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"c4523c277d4e88cf5bd24234b3b32a77364d9482823c092ea63ecabd7431168c","abstract_canon_sha256":"aa31c2b9ec0b528bb515b9beb169d08ceb287159e62d650a0e6f92fb4558de60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:02.537948Z","signature_b64":"HALjM/KehGMP0QctB00tHrP0YFTjWqpTdmPrv6dnR3Ax3um9ct4QtkrqEZ+5nQU1STihAA2jWIfG3J+6BEBVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85bda041a72b74972e6a223b66326d2743cf87c686dffe1764aa92adc3ec7d09","last_reissued_at":"2026-05-17T23:45:02.537482Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:02.537482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.OC","authors_text":"Eduard Gorbunov, Filip Hanzely, Peter Richt\\'arik","submitted_at":"2019-05-27T14:28:13Z","abstract_excerpt":"In this paper we introduce a unified analysis of a large family of variants of proximal stochastic gradient descent ({\\tt SGD}) which so far have required different intuitions, convergence analyses, have different applications, and which have been developed separately in various communities. We show that our framework includes methods with and without the following tricks, and their combinations: variance reduction, importance sampling, mini-batch sampling, quantization, and coordinate sub-sampling. As a by-product, we obtain the first unified theory of {\\tt SGD} and randomized coordinate desc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11261","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":"1905.11261","created_at":"2026-05-17T23:45:02.537570+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11261v1","created_at":"2026-05-17T23:45:02.537570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11261","created_at":"2026-05-17T23:45:02.537570+00:00"},{"alias_kind":"pith_short_12","alias_value":"QW62AQNHFN2J","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QW62AQNHFN2JOLTK","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QW62AQNH","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2409.13428","citing_title":"Methods for Solving Variational Inequalities with Markovian Stochasticity","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5","json":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5.json","graph_json":"https://pith.science/api/pith-number/QW62AQNHFN2JOLTKEI5WMMTNE5/graph.json","events_json":"https://pith.science/api/pith-number/QW62AQNHFN2JOLTKEI5WMMTNE5/events.json","paper":"https://pith.science/paper/QW62AQNH"},"agent_actions":{"view_html":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5","download_json":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5.json","view_paper":"https://pith.science/paper/QW62AQNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11261&json=true","fetch_graph":"https://pith.science/api/pith-number/QW62AQNHFN2JOLTKEI5WMMTNE5/graph.json","fetch_events":"https://pith.science/api/pith-number/QW62AQNHFN2JOLTKEI5WMMTNE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5/action/storage_attestation","attest_author":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5/action/author_attestation","sign_citation":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5/action/citation_signature","submit_replication":"https://pith.science/pith/QW62AQNHFN2JOLTKEI5WMMTNE5/action/replication_record"}},"created_at":"2026-05-17T23:45:02.537570+00:00","updated_at":"2026-05-17T23:45:02.537570+00:00"}