{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6USCNYDQ73KR55YRX5WYLZAPBA","short_pith_number":"pith:6USCNYDQ","schema_version":"1.0","canonical_sha256":"f52426e070fed51ef711bf6d85e40f0805bcbfad666a0111eae97de67fd748d3","source":{"kind":"arxiv","id":"2310.10082","version":3},"attestation_state":"computed","paper":{"title":"A simple uniformly optimal method without line search for convex optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Tianjiao Li","submitted_at":"2023-10-16T05:26:03Z","abstract_excerpt":"Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem parameters (e.g., Lipschitz constant). In this paper, we show that line search is superfluous in attaining the optimal rate of convergence for solving a convex optimization problem whose parameters are not given a priori. In particular, we present a novel accelerated gradient descent type algorithm called auto-conditioned fast gradient method (AC-FGM) that can achieve an optimal $\\mathcal{O}(1/k^2)$ rate of convergence for s"},"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":"2310.10082","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-10-16T05:26:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"34ecad5843238baf8aacda0118d80cf467bba99a7c4cd54281d8119ffeb90567","abstract_canon_sha256":"e8b91479f6943f9333c662a2edc179aae2ebbe72dfbaeda53885defadbbb0cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:14.651157Z","signature_b64":"5TFAyWmRIHX2588dImDzCSHgO9o6OtdIgQSGpRDuvG6QB9tFY5oUXfCvshHwdoGRGH8l5pNfE7Q+17EWgyFuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52426e070fed51ef711bf6d85e40f0805bcbfad666a0111eae97de67fd748d3","last_reissued_at":"2026-07-05T08:56:14.650750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:14.650750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A simple uniformly optimal method without line search for convex optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Tianjiao Li","submitted_at":"2023-10-16T05:26:03Z","abstract_excerpt":"Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem parameters (e.g., Lipschitz constant). In this paper, we show that line search is superfluous in attaining the optimal rate of convergence for solving a convex optimization problem whose parameters are not given a priori. In particular, we present a novel accelerated gradient descent type algorithm called auto-conditioned fast gradient method (AC-FGM) that can achieve an optimal $\\mathcal{O}(1/k^2)$ rate of convergence for s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10082","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/2310.10082/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":"2310.10082","created_at":"2026-07-05T08:56:14.650805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10082v3","created_at":"2026-07-05T08:56:14.650805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10082","created_at":"2026-07-05T08:56:14.650805+00:00"},{"alias_kind":"pith_short_12","alias_value":"6USCNYDQ73KR","created_at":"2026-07-05T08:56:14.650805+00:00"},{"alias_kind":"pith_short_16","alias_value":"6USCNYDQ73KR55YR","created_at":"2026-07-05T08:56:14.650805+00:00"},{"alias_kind":"pith_short_8","alias_value":"6USCNYDQ","created_at":"2026-07-05T08:56:14.650805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.06319","citing_title":"Uniformly Optimal and Parameter-free First-order Methods for Convex and Function-constrained Optimization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14291","citing_title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","ref_index":26,"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":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA","json":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA.json","graph_json":"https://pith.science/api/pith-number/6USCNYDQ73KR55YRX5WYLZAPBA/graph.json","events_json":"https://pith.science/api/pith-number/6USCNYDQ73KR55YRX5WYLZAPBA/events.json","paper":"https://pith.science/paper/6USCNYDQ"},"agent_actions":{"view_html":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA","download_json":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA.json","view_paper":"https://pith.science/paper/6USCNYDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10082&json=true","fetch_graph":"https://pith.science/api/pith-number/6USCNYDQ73KR55YRX5WYLZAPBA/graph.json","fetch_events":"https://pith.science/api/pith-number/6USCNYDQ73KR55YRX5WYLZAPBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA/action/storage_attestation","attest_author":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA/action/author_attestation","sign_citation":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA/action/citation_signature","submit_replication":"https://pith.science/pith/6USCNYDQ73KR55YRX5WYLZAPBA/action/replication_record"}},"created_at":"2026-07-05T08:56:14.650805+00:00","updated_at":"2026-07-05T08:56:14.650805+00:00"}