{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RZJRGS4BBCCKVP3QNWANTF2AJA","short_pith_number":"pith:RZJRGS4B","schema_version":"1.0","canonical_sha256":"8e53134b810884aabf706d80d99740483c604f7e5dde79534a2930063cc2697d","source":{"kind":"arxiv","id":"2310.12139","version":3},"attestation_state":"computed","paper":{"title":"Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Yuyuan Ouyang, Zhe Zhang","submitted_at":"2023-10-18T17:50:13Z","abstract_excerpt":"We propose novel optimal and parameter-free algorithms for computing an approximate solution with small (projected) gradient norm. Specifically, for computing an approximate solution such that the norm of its (projected) gradient does not exceed $\\varepsilon$, we obtain the following results: a) for the convex case, the total number of gradient evaluations is bounded by $O(1)\\sqrt{L\\|x_0 - x^*\\|/\\varepsilon}$, where $L$ is the Lipschitz constant of the gradient and $x^*$ is any optimal solution; b) for the strongly convex case, the total number of gradient evaluations is bounded by $O(1)\\sqrt{"},"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":"2310.12139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-18T17:50:13Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"1faa80063274fb8812e0a627e8a85a3053e50f5ec1cacdb1cc069c7ba775bac8","abstract_canon_sha256":"5caefb623543755b15521047c15e7f2e82aa28b95bf95354416a26a3c5820353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:46.513690Z","signature_b64":"NnCqssUnRaXvIH7vhQL9RemmgZMkswX9qVDzsCOx3YT5C2OaVsfi/W1nGS7ZHDbK7qZr4SkimFYThktHhfNJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e53134b810884aabf706d80d99740483c604f7e5dde79534a2930063cc2697d","last_reissued_at":"2026-07-05T09:35:46.513179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:46.513179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Yuyuan Ouyang, Zhe Zhang","submitted_at":"2023-10-18T17:50:13Z","abstract_excerpt":"We propose novel optimal and parameter-free algorithms for computing an approximate solution with small (projected) gradient norm. Specifically, for computing an approximate solution such that the norm of its (projected) gradient does not exceed $\\varepsilon$, we obtain the following results: a) for the convex case, the total number of gradient evaluations is bounded by $O(1)\\sqrt{L\\|x_0 - x^*\\|/\\varepsilon}$, where $L$ is the Lipschitz constant of the gradient and $x^*$ is any optimal solution; b) for the strongly convex case, the total number of gradient evaluations is bounded by $O(1)\\sqrt{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12139","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/2310.12139/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":"2310.12139","created_at":"2026-07-05T09:35:46.513239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12139v3","created_at":"2026-07-05T09:35:46.513239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12139","created_at":"2026-07-05T09:35:46.513239+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZJRGS4BBCCK","created_at":"2026-07-05T09:35:46.513239+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZJRGS4BBCCKVP3Q","created_at":"2026-07-05T09:35:46.513239+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZJRGS4B","created_at":"2026-07-05T09:35:46.513239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14291","citing_title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23492","citing_title":"Universal and Parameter-free Gradient Sliding for Composite Optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18604","citing_title":"Efficient Gradient Methods for Distributed Saddle Problems","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11043","citing_title":"A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18321","citing_title":"Accuracy Certificates for Convex Optimization at Accelerated Rates via Primal-Dual Averaging","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA","json":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA.json","graph_json":"https://pith.science/api/pith-number/RZJRGS4BBCCKVP3QNWANTF2AJA/graph.json","events_json":"https://pith.science/api/pith-number/RZJRGS4BBCCKVP3QNWANTF2AJA/events.json","paper":"https://pith.science/paper/RZJRGS4B"},"agent_actions":{"view_html":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA","download_json":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA.json","view_paper":"https://pith.science/paper/RZJRGS4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12139&json=true","fetch_graph":"https://pith.science/api/pith-number/RZJRGS4BBCCKVP3QNWANTF2AJA/graph.json","fetch_events":"https://pith.science/api/pith-number/RZJRGS4BBCCKVP3QNWANTF2AJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA/action/storage_attestation","attest_author":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA/action/author_attestation","sign_citation":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA/action/citation_signature","submit_replication":"https://pith.science/pith/RZJRGS4BBCCKVP3QNWANTF2AJA/action/replication_record"}},"created_at":"2026-07-05T09:35:46.513239+00:00","updated_at":"2026-07-05T09:35:46.513239+00:00"}