{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ON6OOD6LL5OT6TOAC6YP4HWTYO","short_pith_number":"pith:ON6OOD6L","schema_version":"1.0","canonical_sha256":"737ce70fcb5f5d3f4dc017b0fe1ed3c3b2862916d39b23cc85c30ac90a50c48f","source":{"kind":"arxiv","id":"1711.07564","version":1},"attestation_state":"computed","paper":{"title":"Unbiased Simulation for Optimizing Stochastic Function Compositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"math.OC","authors_text":"Chaoxu Zhou, Donald Goldfarb, Fengpei Li, Garud Iyengar, Jose Blanchet","submitted_at":"2017-11-20T21:58:01Z","abstract_excerpt":"In this paper, we introduce an unbiased gradient simulation algorithms for solving convex optimization problem with stochastic function compositions. We show that the unbiased gradient generated from the algorithm has finite variance and finite expected computation cost. We then combined the unbiased gradient simulation with two variance reduced algorithms (namely SVRG and SCSG) and showed that the proposed optimization algorithms based on unbiased gradient simulations exhibit satisfactory convergence properties. Specifically, in the SVRG case, the algorithm with simulated gradient can be show"},"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":"1711.07564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-11-20T21:58:01Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"3130b54d7365abee175be7a341684d3c91bcdfbcfab6b9a2a1132d66ce7a6c45","abstract_canon_sha256":"0e8e65d0905d6c96734b1888bf4d8f5b9d5063783955232260efc0f801bf5694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:58.684415Z","signature_b64":"Se28zkIC/099wQUrHChcPi8xYgqQoUOoEnKI0Ru+4r/RSWmIkprkpCvoYfzZQXXlTnML4wR6zFpmnUFtwtguAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"737ce70fcb5f5d3f4dc017b0fe1ed3c3b2862916d39b23cc85c30ac90a50c48f","last_reissued_at":"2026-05-18T00:29:58.683827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:58.683827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiased Simulation for Optimizing Stochastic Function Compositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"math.OC","authors_text":"Chaoxu Zhou, Donald Goldfarb, Fengpei Li, Garud Iyengar, Jose Blanchet","submitted_at":"2017-11-20T21:58:01Z","abstract_excerpt":"In this paper, we introduce an unbiased gradient simulation algorithms for solving convex optimization problem with stochastic function compositions. We show that the unbiased gradient generated from the algorithm has finite variance and finite expected computation cost. We then combined the unbiased gradient simulation with two variance reduced algorithms (namely SVRG and SCSG) and showed that the proposed optimization algorithms based on unbiased gradient simulations exhibit satisfactory convergence properties. Specifically, in the SVRG case, the algorithm with simulated gradient can be show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07564","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":"1711.07564","created_at":"2026-05-18T00:29:58.683922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07564v1","created_at":"2026-05-18T00:29:58.683922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07564","created_at":"2026-05-18T00:29:58.683922+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON6OOD6LL5OT","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON6OOD6LL5OT6TOA","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON6OOD6L","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14075","citing_title":"Multistage Conditional Compositional Optimization","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO","json":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO.json","graph_json":"https://pith.science/api/pith-number/ON6OOD6LL5OT6TOAC6YP4HWTYO/graph.json","events_json":"https://pith.science/api/pith-number/ON6OOD6LL5OT6TOAC6YP4HWTYO/events.json","paper":"https://pith.science/paper/ON6OOD6L"},"agent_actions":{"view_html":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO","download_json":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO.json","view_paper":"https://pith.science/paper/ON6OOD6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07564&json=true","fetch_graph":"https://pith.science/api/pith-number/ON6OOD6LL5OT6TOAC6YP4HWTYO/graph.json","fetch_events":"https://pith.science/api/pith-number/ON6OOD6LL5OT6TOAC6YP4HWTYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO/action/storage_attestation","attest_author":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO/action/author_attestation","sign_citation":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO/action/citation_signature","submit_replication":"https://pith.science/pith/ON6OOD6LL5OT6TOAC6YP4HWTYO/action/replication_record"}},"created_at":"2026-05-18T00:29:58.683922+00:00","updated_at":"2026-05-18T00:29:58.683922+00:00"}