{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4G3VCANRFN7VJAU5LB4D2WVYFP","short_pith_number":"pith:4G3VCANR","schema_version":"1.0","canonical_sha256":"e1b75101b12b7f54829d58783d5ab82bdeab572a42f465cc70d074fe57a35c31","source":{"kind":"arxiv","id":"2008.09055","version":1},"attestation_state":"computed","paper":{"title":"An Optimal Hybrid Variance-Reduced Algorithm for Stochastic Composite Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Deyi Liu, Lam M. Nguyen, Quoc Tran-Dinh","submitted_at":"2020-08-20T16:15:12Z","abstract_excerpt":"In this note we propose a new variant of the hybrid variance-reduced proximal gradient method in [7] to solve a common stochastic composite nonconvex optimization problem under standard assumptions. We simply replace the independent unbiased estimator in our hybrid- SARAH estimator introduced in [7] by the stochastic gradient evaluated at the same sample, leading to the identical momentum-SARAH estimator introduced in [2]. This allows us to save one stochastic gradient per iteration compared to [7], and only requires two samples per iteration. Our algorithm is very simple and achieves optimal "},"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":"2008.09055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-20T16:15:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"614ae12c8f4ef525ab06e87e67228a83c789d284cad948a93c2a7d6b0c98da61","abstract_canon_sha256":"21d92984fa424322a51731cec987243923ee3d71e83bb95afa9d4bd1a8b287be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:39.265126Z","signature_b64":"JvtzDQfO3k/Dw8omlspYeImWywmg0UJ8pYwtEmovTqE9r39hOvcFKO1rbs/29/yGcCcTm4baYOniHI2SGRozBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1b75101b12b7f54829d58783d5ab82bdeab572a42f465cc70d074fe57a35c31","last_reissued_at":"2026-07-05T01:28:39.264735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:39.264735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Optimal Hybrid Variance-Reduced Algorithm for Stochastic Composite Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Deyi Liu, Lam M. Nguyen, Quoc Tran-Dinh","submitted_at":"2020-08-20T16:15:12Z","abstract_excerpt":"In this note we propose a new variant of the hybrid variance-reduced proximal gradient method in [7] to solve a common stochastic composite nonconvex optimization problem under standard assumptions. We simply replace the independent unbiased estimator in our hybrid- SARAH estimator introduced in [7] by the stochastic gradient evaluated at the same sample, leading to the identical momentum-SARAH estimator introduced in [2]. This allows us to save one stochastic gradient per iteration compared to [7], and only requires two samples per iteration. Our algorithm is very simple and achieves optimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09055","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/2008.09055/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":"2008.09055","created_at":"2026-07-05T01:28:39.264792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.09055v1","created_at":"2026-07-05T01:28:39.264792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09055","created_at":"2026-07-05T01:28:39.264792+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G3VCANRFN7V","created_at":"2026-07-05T01:28:39.264792+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G3VCANRFN7VJAU5","created_at":"2026-07-05T01:28:39.264792+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G3VCANR","created_at":"2026-07-05T01:28:39.264792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20866","citing_title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18174","citing_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15388","citing_title":"Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08871","citing_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07795","citing_title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP","json":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP.json","graph_json":"https://pith.science/api/pith-number/4G3VCANRFN7VJAU5LB4D2WVYFP/graph.json","events_json":"https://pith.science/api/pith-number/4G3VCANRFN7VJAU5LB4D2WVYFP/events.json","paper":"https://pith.science/paper/4G3VCANR"},"agent_actions":{"view_html":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP","download_json":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP.json","view_paper":"https://pith.science/paper/4G3VCANR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.09055&json=true","fetch_graph":"https://pith.science/api/pith-number/4G3VCANRFN7VJAU5LB4D2WVYFP/graph.json","fetch_events":"https://pith.science/api/pith-number/4G3VCANRFN7VJAU5LB4D2WVYFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP/action/storage_attestation","attest_author":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP/action/author_attestation","sign_citation":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP/action/citation_signature","submit_replication":"https://pith.science/pith/4G3VCANRFN7VJAU5LB4D2WVYFP/action/replication_record"}},"created_at":"2026-07-05T01:28:39.264792+00:00","updated_at":"2026-07-05T01:28:39.264792+00:00"}