{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EUFM5VDDIB7FHAAL5GUAZOI5CD","short_pith_number":"pith:EUFM5VDD","schema_version":"1.0","canonical_sha256":"250aced463407e53800be9a80cb91d10e20279d1dcf239880cb485184f5a5f95","source":{"kind":"arxiv","id":"2102.08352","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Variance Reduction for Variational Inequality Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Ahmet Alacaoglu, Yura Malitsky","submitted_at":"2021-02-16T18:39:16Z","abstract_excerpt":"We propose stochastic variance reduced algorithms for solving convex-concave saddle point problems, monotone variational inequalities, and monotone inclusions. Our framework applies to extragradient, forward-backward-forward, and forward-reflected-backward methods both in Euclidean and Bregman setups. All proposed methods converge in the same setting as their deterministic counterparts and they either match or improve the best-known complexities for solving structured min-max problems. Our results reinforce the correspondence between variance reduction in variational inequalities and minimizat"},"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":"2102.08352","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-02-16T18:39:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bb01e91d9feb11fd4f355bee6f7f3e74bbafde0be68a5955bb28e3bdd1ff4d5c","abstract_canon_sha256":"e78ce9b0a97103be3bff21701990e1e3e4b97c39fb7bb19f27ade9d61547caf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:50.786247Z","signature_b64":"gb7EPxI8LJlUCTKPMQcRh5yPoa/FIPpKYv2hPEZ5sj0vugs6xbawUYi7cWMuOY0m8DqPLA2PoNCtT71qVqy/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"250aced463407e53800be9a80cb91d10e20279d1dcf239880cb485184f5a5f95","last_reissued_at":"2026-07-05T04:30:50.785838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:50.785838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Variance Reduction for Variational Inequality Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Ahmet Alacaoglu, Yura Malitsky","submitted_at":"2021-02-16T18:39:16Z","abstract_excerpt":"We propose stochastic variance reduced algorithms for solving convex-concave saddle point problems, monotone variational inequalities, and monotone inclusions. Our framework applies to extragradient, forward-backward-forward, and forward-reflected-backward methods both in Euclidean and Bregman setups. All proposed methods converge in the same setting as their deterministic counterparts and they either match or improve the best-known complexities for solving structured min-max problems. Our results reinforce the correspondence between variance reduction in variational inequalities and minimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08352","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/2102.08352/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":"2102.08352","created_at":"2026-07-05T04:30:50.785889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08352v2","created_at":"2026-07-05T04:30:50.785889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08352","created_at":"2026-07-05T04:30:50.785889+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUFM5VDDIB7F","created_at":"2026-07-05T04:30:50.785889+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUFM5VDDIB7FHAAL","created_at":"2026-07-05T04:30:50.785889+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUFM5VDD","created_at":"2026-07-05T04:30:50.785889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16875","citing_title":"Stochastic Optimization and Data Science","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD","json":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD.json","graph_json":"https://pith.science/api/pith-number/EUFM5VDDIB7FHAAL5GUAZOI5CD/graph.json","events_json":"https://pith.science/api/pith-number/EUFM5VDDIB7FHAAL5GUAZOI5CD/events.json","paper":"https://pith.science/paper/EUFM5VDD"},"agent_actions":{"view_html":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD","download_json":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD.json","view_paper":"https://pith.science/paper/EUFM5VDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08352&json=true","fetch_graph":"https://pith.science/api/pith-number/EUFM5VDDIB7FHAAL5GUAZOI5CD/graph.json","fetch_events":"https://pith.science/api/pith-number/EUFM5VDDIB7FHAAL5GUAZOI5CD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD/action/storage_attestation","attest_author":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD/action/author_attestation","sign_citation":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD/action/citation_signature","submit_replication":"https://pith.science/pith/EUFM5VDDIB7FHAAL5GUAZOI5CD/action/replication_record"}},"created_at":"2026-07-05T04:30:50.785889+00:00","updated_at":"2026-07-05T04:30:50.785889+00:00"}