{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SY3ZSV2JMFPC7YNXRMT4ENF5Q2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5cd2ca25227d96e2d12d005e7e4a075b8c28fc27ef9bdac58cc9eb96e4e2cb26","cross_cats_sorted":["cs.AI","cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T09:11:31Z","title_canon_sha256":"3b1706b3f4a521f47bfedd7a9f47a9b94e8af6d73aac3a000656f43aaf6ec35e"},"schema_version":"1.0","source":{"id":"2008.10898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.10898","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.10898v3","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10898","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"SY3ZSV2JMFPC","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"SY3ZSV2JMFPC7YNX","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"SY3ZSV2J","created_at":"2026-07-05T02:48:33Z"}],"graph_snapshots":[{"event_id":"sha256:f5b55069fd4b491424b579db30ee0f465d1e877941b5423d86fd69d39a9d935c","target":"graph","created_at":"2026-07-05T02:48:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.10898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel stochastic gradient estimator -- ProbAbilistic Gradient Estimator (PAGE) -- for nonconvex optimization. PAGE is easy to implement as it is designed via a small adjustment to vanilla SGD: in each iteration, PAGE uses the vanilla minibatch SGD update with probability $p_t$ or reuses the previous gradient with a small adjustment, at a much lower computational cost, with probability $1-p_t$. We give a simple formula for the optimal choice of $p_t$. Moreover, we prove the first tight lower bound $\\Omega(n+\\frac{\\sqrt{n}}{\\epsilon^2})$ for nonconvex finite-sum probl","authors_text":"Hongyan Bao, Peter Richt\\'arik, Xiangliang Zhang, Zhize Li","cross_cats":["cs.AI","cs.DS","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T09:11:31Z","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10898","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a8f6bb70f5c8b5ef0f1a25fe36b4182e4ee4675cfbe050a838460fd84e1ffa20","target":"record","created_at":"2026-07-05T02:48:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5cd2ca25227d96e2d12d005e7e4a075b8c28fc27ef9bdac58cc9eb96e4e2cb26","cross_cats_sorted":["cs.AI","cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T09:11:31Z","title_canon_sha256":"3b1706b3f4a521f47bfedd7a9f47a9b94e8af6d73aac3a000656f43aaf6ec35e"},"schema_version":"1.0","source":{"id":"2008.10898","kind":"arxiv","version":3}},"canonical_sha256":"9637995749615e2fe1b78b27c234bd86987e78192c01839885f883ad35a7b146","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9637995749615e2fe1b78b27c234bd86987e78192c01839885f883ad35a7b146","first_computed_at":"2026-07-05T02:48:33.815464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:33.815464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2EO9mXXNuiQWWVxhZm99DexK6cBi2j/G1aqQkctK0Zu+RVBQOGNrChtDh/gjd8fnSLHcZrx6LdCTgI5W9jYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:33.815960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.10898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f6bb70f5c8b5ef0f1a25fe36b4182e4ee4675cfbe050a838460fd84e1ffa20","sha256:f5b55069fd4b491424b579db30ee0f465d1e877941b5423d86fd69d39a9d935c"],"state_sha256":"2e7e1472e0b268e66f0d278eb39e2e93b4151d339a76e4595cc2277e5eba5764"}