{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6DISIHWMSXLSWE3QPD3FK5TEUK","short_pith_number":"pith:6DISIHWM","schema_version":"1.0","canonical_sha256":"f0d1241ecc95d72b137078f6557664a28b15cef0d8ea55f8680eed7f959721da","source":{"kind":"arxiv","id":"1905.05920","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Dzung T. Phan, Lam M. Nguyen, Nhan H. Pham, Quoc Tran-Dinh","submitted_at":"2019-05-15T02:38:03Z","abstract_excerpt":"We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to some useful property on its variance. We limit our consideration to a hybrid SARAH-SGD for nonconvex expectation problems. However, our idea can be extended to handle a broader class of estimators in both convex and nonconvex settings. We propose a new single-loop stochastic gradient descent algorithm that can achieve $O(\\max\\{\\sigma^3\\varepsilon^{-1},\\sigma\\v"},"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":"1905.05920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-05-15T02:38:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d542134fa1e5f437aa063a7c456b06d3331ba85a74d16cc0f757d91707815cd9","abstract_canon_sha256":"6c024577c21dc97f92e02a4b017adc3bddca5fa1eeb2e08e0690dfdc11ff75bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:08.097137Z","signature_b64":"eo7XQuc1nMR1eCViy7lYOvx1j712NwGupXVuP00FE0Prufo+NhCfJ/pR/4OpmENlDD/Do+ulVRbeuWuDjIYMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d1241ecc95d72b137078f6557664a28b15cef0d8ea55f8680eed7f959721da","last_reissued_at":"2026-05-17T23:46:08.096547Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:08.096547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Dzung T. Phan, Lam M. Nguyen, Nhan H. Pham, Quoc Tran-Dinh","submitted_at":"2019-05-15T02:38:03Z","abstract_excerpt":"We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to some useful property on its variance. We limit our consideration to a hybrid SARAH-SGD for nonconvex expectation problems. However, our idea can be extended to handle a broader class of estimators in both convex and nonconvex settings. We propose a new single-loop stochastic gradient descent algorithm that can achieve $O(\\max\\{\\sigma^3\\varepsilon^{-1},\\sigma\\v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05920","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":"1905.05920","created_at":"2026-05-17T23:46:08.096637+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05920v1","created_at":"2026-05-17T23:46:08.096637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05920","created_at":"2026-05-17T23:46:08.096637+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DISIHWMSXLS","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DISIHWMSXLSWE3Q","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DISIHWM","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.20866","citing_title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18174","citing_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","ref_index":119,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15388","citing_title":"Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation","ref_index":133,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08871","citing_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07795","citing_title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK","json":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK.json","graph_json":"https://pith.science/api/pith-number/6DISIHWMSXLSWE3QPD3FK5TEUK/graph.json","events_json":"https://pith.science/api/pith-number/6DISIHWMSXLSWE3QPD3FK5TEUK/events.json","paper":"https://pith.science/paper/6DISIHWM"},"agent_actions":{"view_html":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK","download_json":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK.json","view_paper":"https://pith.science/paper/6DISIHWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05920&json=true","fetch_graph":"https://pith.science/api/pith-number/6DISIHWMSXLSWE3QPD3FK5TEUK/graph.json","fetch_events":"https://pith.science/api/pith-number/6DISIHWMSXLSWE3QPD3FK5TEUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK/action/storage_attestation","attest_author":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK/action/author_attestation","sign_citation":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK/action/citation_signature","submit_replication":"https://pith.science/pith/6DISIHWMSXLSWE3QPD3FK5TEUK/action/replication_record"}},"created_at":"2026-05-17T23:46:08.096637+00:00","updated_at":"2026-05-17T23:46:08.096637+00:00"}