{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SBIQIK7TTUDK3JCLFUXENV5GZC","short_pith_number":"pith:SBIQIK7T","schema_version":"1.0","canonical_sha256":"9051042bf39d06ada44b2d2e46d7a6c8829f31fa2f7786d4395b15aca8674a85","source":{"kind":"arxiv","id":"2106.13781","version":1},"attestation_state":"computed","paper":{"title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Tianyi Chen, Wotao Yin, Yuejiao Sun","submitted_at":"2021-06-25T17:33:51Z","abstract_excerpt":"Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often treat them separately, and thus develop problem-specific algorithms and their analyses. Among various exciting developments, simple SGD-type updates (potentially on multiple variables) are still prevalent in solving this class of nested problems, but they are believed to have slower convergence rate compared to that of the non-nested problems. This paper unifie"},"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":"2106.13781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-25T17:33:51Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"3c7c4ee787260c80789f10c77ee6dbc59c656e0e14b9929ebf93f2522bfa59e7","abstract_canon_sha256":"b76ac1c479e34ec7fe46c1793e4aeed08dee55dbd48da20531235165824debe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:26.116902Z","signature_b64":"6kmYl34gt9jFSKfLHv1GjLtSvl9w1pVGm4ggxpzN/3xeMa/kkAiGFidltf98HOuW9+lkPLtotZ1gDz4naONAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9051042bf39d06ada44b2d2e46d7a6c8829f31fa2f7786d4395b15aca8674a85","last_reissued_at":"2026-07-05T02:52:26.116421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:26.116421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Tianyi Chen, Wotao Yin, Yuejiao Sun","submitted_at":"2021-06-25T17:33:51Z","abstract_excerpt":"Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often treat them separately, and thus develop problem-specific algorithms and their analyses. Among various exciting developments, simple SGD-type updates (potentially on multiple variables) are still prevalent in solving this class of nested problems, but they are believed to have slower convergence rate compared to that of the non-nested problems. This paper unifie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13781","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.13781/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":"2106.13781","created_at":"2026-07-05T02:52:26.116479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13781v1","created_at":"2026-07-05T02:52:26.116479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13781","created_at":"2026-07-05T02:52:26.116479+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBIQIK7TTUDK","created_at":"2026-07-05T02:52:26.116479+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBIQIK7TTUDK3JCL","created_at":"2026-07-05T02:52:26.116479+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBIQIK7T","created_at":"2026-07-05T02:52:26.116479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22433","citing_title":"Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC","json":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC.json","graph_json":"https://pith.science/api/pith-number/SBIQIK7TTUDK3JCLFUXENV5GZC/graph.json","events_json":"https://pith.science/api/pith-number/SBIQIK7TTUDK3JCLFUXENV5GZC/events.json","paper":"https://pith.science/paper/SBIQIK7T"},"agent_actions":{"view_html":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC","download_json":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC.json","view_paper":"https://pith.science/paper/SBIQIK7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13781&json=true","fetch_graph":"https://pith.science/api/pith-number/SBIQIK7TTUDK3JCLFUXENV5GZC/graph.json","fetch_events":"https://pith.science/api/pith-number/SBIQIK7TTUDK3JCLFUXENV5GZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC/action/storage_attestation","attest_author":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC/action/author_attestation","sign_citation":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC/action/citation_signature","submit_replication":"https://pith.science/pith/SBIQIK7TTUDK3JCLFUXENV5GZC/action/replication_record"}},"created_at":"2026-07-05T02:52:26.116479+00:00","updated_at":"2026-07-05T02:52:26.116479+00:00"}