{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VFC7MD25PA3MDFHOHI4WQDAKKA","short_pith_number":"pith:VFC7MD25","schema_version":"1.0","canonical_sha256":"a945f60f5d7836c194ee3a39680c0a5035a989c17677f730cf91da90d1eece8d","source":{"kind":"arxiv","id":"1810.10690","version":3},"attestation_state":"computed","paper":{"title":"SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kaiyi Ji, Vahid Tarokh, Yingbin Liang, Yi Zhou, Zhe Wang","submitted_at":"2018-10-25T02:18:03Z","abstract_excerpt":"SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses an accuracy-dependent stepsize that slows down the convergence in practice, and cannot handle objective functions that involve nonsmooth regularizers. In this paper, we propose SpiderBoost as an improved scheme, which allows to use a much larger constant-level stepsize while maintaining the same near-optimal oracle complexity, and can be extended with proximal mapping to handl"},"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":"1810.10690","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-25T02:18:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e1cfd1b76acfa8f8786d714c56875895cf11f501553330194db489b568d82d77","abstract_canon_sha256":"8bd0103865799d00ca822196716161d5e2cb56b544cba553c52cbb2dd0b745c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:05.996862Z","signature_b64":"HkL8F/6Bj7lT9SvduXWTxWGbo9f6ONgdQJXIli/CO1VIVFJut2+UFThBAbTYC+uPm/MfZTzehcCMhCyKV0QCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a945f60f5d7836c194ee3a39680c0a5035a989c17677f730cf91da90d1eece8d","last_reissued_at":"2026-07-05T01:03:05.996404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:05.996404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kaiyi Ji, Vahid Tarokh, Yingbin Liang, Yi Zhou, Zhe Wang","submitted_at":"2018-10-25T02:18:03Z","abstract_excerpt":"SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses an accuracy-dependent stepsize that slows down the convergence in practice, and cannot handle objective functions that involve nonsmooth regularizers. In this paper, we propose SpiderBoost as an improved scheme, which allows to use a much larger constant-level stepsize while maintaining the same near-optimal oracle complexity, and can be extended with proximal mapping to handl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10690","kind":"arxiv","version":3},"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/1810.10690/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":"1810.10690","created_at":"2026-07-05T01:03:05.996466+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10690v3","created_at":"2026-07-05T01:03:05.996466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10690","created_at":"2026-07-05T01:03:05.996466+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFC7MD25PA3M","created_at":"2026-07-05T01:03:05.996466+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFC7MD25PA3MDFHO","created_at":"2026-07-05T01:03:05.996466+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFC7MD25","created_at":"2026-07-05T01:03:05.996466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.10186","citing_title":"A Stochastic Composite Gradient Method with Incremental Variance Reduction","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15314","citing_title":"Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA","json":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA.json","graph_json":"https://pith.science/api/pith-number/VFC7MD25PA3MDFHOHI4WQDAKKA/graph.json","events_json":"https://pith.science/api/pith-number/VFC7MD25PA3MDFHOHI4WQDAKKA/events.json","paper":"https://pith.science/paper/VFC7MD25"},"agent_actions":{"view_html":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA","download_json":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA.json","view_paper":"https://pith.science/paper/VFC7MD25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10690&json=true","fetch_graph":"https://pith.science/api/pith-number/VFC7MD25PA3MDFHOHI4WQDAKKA/graph.json","fetch_events":"https://pith.science/api/pith-number/VFC7MD25PA3MDFHOHI4WQDAKKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA/action/storage_attestation","attest_author":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA/action/author_attestation","sign_citation":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA/action/citation_signature","submit_replication":"https://pith.science/pith/VFC7MD25PA3MDFHOHI4WQDAKKA/action/replication_record"}},"created_at":"2026-07-05T01:03:05.996466+00:00","updated_at":"2026-07-05T01:03:05.996466+00:00"}