{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4OP6Z2PZOT4EVMZM3CNB3JR6YG","short_pith_number":"pith:4OP6Z2PZ","schema_version":"1.0","canonical_sha256":"e39fece9f974f84ab32cd89a1da63ec192e0a01bf72854393c6481598b2116fe","source":{"kind":"arxiv","id":"2502.21099","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Ganzhao Yuan","submitted_at":"2025-02-28T14:37:56Z","abstract_excerpt":"This paper proposes {\\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing composite nonconvex finite-sum functions. It integrates three acceleration techniques: adaptive stepsizes, Nesterov's extrapolation, and the recursive stochastic path-integrated estimator SPIDER. Unlike existing methods that adjust the stepsize factor using historical gradients, {\\sf AEPG-SPIDER} relies on past iterate differences for its update. While targeting stochastic finite-sum problems, {\\sf AEPG-SPIDER} simplifies to {\\sf AEPG} in the full-batch, non-st"},"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":"2502.21099","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-28T14:37:56Z","cross_cats_sorted":["cs.CV","cs.NA","math.NA"],"title_canon_sha256":"ad49b7dc34a383553e76b7135e326f6accb0c4330f7acf8945f017ab5b667aa3","abstract_canon_sha256":"341937bb882844395c1ea515ae10c81bdf949eb17eccc1ad07c341229bcc3ce0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:46.576354Z","signature_b64":"PuI/rWXoF5gLrjhYxATirhccHttgEZODk9fK9glMer6uQEjfuCdnF42PSFYfnR8rX6WrVM3GW4cDHJFoZa/tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e39fece9f974f84ab32cd89a1da63ec192e0a01bf72854393c6481598b2116fe","last_reissued_at":"2026-07-05T11:04:46.575798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:46.575798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Ganzhao Yuan","submitted_at":"2025-02-28T14:37:56Z","abstract_excerpt":"This paper proposes {\\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing composite nonconvex finite-sum functions. It integrates three acceleration techniques: adaptive stepsizes, Nesterov's extrapolation, and the recursive stochastic path-integrated estimator SPIDER. Unlike existing methods that adjust the stepsize factor using historical gradients, {\\sf AEPG-SPIDER} relies on past iterate differences for its update. While targeting stochastic finite-sum problems, {\\sf AEPG-SPIDER} simplifies to {\\sf AEPG} in the full-batch, non-st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21099","kind":"arxiv","version":2},"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/2502.21099/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":"2502.21099","created_at":"2026-07-05T11:04:46.575863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.21099v2","created_at":"2026-07-05T11:04:46.575863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21099","created_at":"2026-07-05T11:04:46.575863+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OP6Z2PZOT4E","created_at":"2026-07-05T11:04:46.575863+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OP6Z2PZOT4EVMZM","created_at":"2026-07-05T11:04:46.575863+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OP6Z2PZ","created_at":"2026-07-05T11:04:46.575863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG","json":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG.json","graph_json":"https://pith.science/api/pith-number/4OP6Z2PZOT4EVMZM3CNB3JR6YG/graph.json","events_json":"https://pith.science/api/pith-number/4OP6Z2PZOT4EVMZM3CNB3JR6YG/events.json","paper":"https://pith.science/paper/4OP6Z2PZ"},"agent_actions":{"view_html":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG","download_json":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG.json","view_paper":"https://pith.science/paper/4OP6Z2PZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.21099&json=true","fetch_graph":"https://pith.science/api/pith-number/4OP6Z2PZOT4EVMZM3CNB3JR6YG/graph.json","fetch_events":"https://pith.science/api/pith-number/4OP6Z2PZOT4EVMZM3CNB3JR6YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG/action/storage_attestation","attest_author":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG/action/author_attestation","sign_citation":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG/action/citation_signature","submit_replication":"https://pith.science/pith/4OP6Z2PZOT4EVMZM3CNB3JR6YG/action/replication_record"}},"created_at":"2026-07-05T11:04:46.575863+00:00","updated_at":"2026-07-05T11:04:46.575863+00:00"}