{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XXUSS5MZFH6DKIX4MMCJFZIE3C","short_pith_number":"pith:XXUSS5MZ","schema_version":"1.0","canonical_sha256":"bde929759929fc3522fc630492e504d8a4737ebdf8c9f0b7a630df9b48fd54d6","source":{"kind":"arxiv","id":"2412.04427","version":2},"attestation_state":"computed","paper":{"title":"A Proof of the Exact Convergence Rate of Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jungbin Kim","submitted_at":"2024-12-05T18:51:26Z","abstract_excerpt":"We prove the exact worst-case convergence rate of gradient descent for smooth strongly convex optimization on $\\mathbb{R}^d$. Concretely, assuming that the objective function $f$ is $\\mu$-strongly convex and $L$-smooth, we identify the smallest possible value of $\\tau$ for which the inequality $f(x_{N})-f_{*}\\leq\\tau\\|x_{0}-x_{*}\\|^{2}$ always holds. The result was previously conjectured by Drori and Teboulle for the case $\\mu=0$, and by Taylor, Hendrickx, and Glineur for the case $\\mu>0$."},"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":"2412.04427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-05T18:51:26Z","cross_cats_sorted":[],"title_canon_sha256":"d99332bbaff480be899dc04aa93ea4bbdd165481e5742d81b41f7c51b16affcc","abstract_canon_sha256":"fd5a56d718cb3fd87097fd22f1eae4c1d779884be6ecdee508cfd2c324feb00a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:24.068576Z","signature_b64":"+ZifdAESzsCrMun2i0DstC0uABaJrWc6CMHDcXkbIJZ3J8NTyG+aeqdv4v9e5RcbBwmdfItn0ZYOBqxxOCdqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bde929759929fc3522fc630492e504d8a4737ebdf8c9f0b7a630df9b48fd54d6","last_reissued_at":"2026-07-05T10:39:24.068085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:24.068085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Proof of the Exact Convergence Rate of Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jungbin Kim","submitted_at":"2024-12-05T18:51:26Z","abstract_excerpt":"We prove the exact worst-case convergence rate of gradient descent for smooth strongly convex optimization on $\\mathbb{R}^d$. Concretely, assuming that the objective function $f$ is $\\mu$-strongly convex and $L$-smooth, we identify the smallest possible value of $\\tau$ for which the inequality $f(x_{N})-f_{*}\\leq\\tau\\|x_{0}-x_{*}\\|^{2}$ always holds. The result was previously conjectured by Drori and Teboulle for the case $\\mu=0$, and by Taylor, Hendrickx, and Glineur for the case $\\mu>0$."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04427","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/2412.04427/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":"2412.04427","created_at":"2026-07-05T10:39:24.068143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04427v2","created_at":"2026-07-05T10:39:24.068143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04427","created_at":"2026-07-05T10:39:24.068143+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXUSS5MZFH6D","created_at":"2026-07-05T10:39:24.068143+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXUSS5MZFH6DKIX4","created_at":"2026-07-05T10:39:24.068143+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXUSS5MZ","created_at":"2026-07-05T10:39:24.068143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02231","citing_title":"A Theory of Composition and Duality of Extremal Optimal Fixed-Point Algorithms","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C","json":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C.json","graph_json":"https://pith.science/api/pith-number/XXUSS5MZFH6DKIX4MMCJFZIE3C/graph.json","events_json":"https://pith.science/api/pith-number/XXUSS5MZFH6DKIX4MMCJFZIE3C/events.json","paper":"https://pith.science/paper/XXUSS5MZ"},"agent_actions":{"view_html":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C","download_json":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C.json","view_paper":"https://pith.science/paper/XXUSS5MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04427&json=true","fetch_graph":"https://pith.science/api/pith-number/XXUSS5MZFH6DKIX4MMCJFZIE3C/graph.json","fetch_events":"https://pith.science/api/pith-number/XXUSS5MZFH6DKIX4MMCJFZIE3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C/action/storage_attestation","attest_author":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C/action/author_attestation","sign_citation":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C/action/citation_signature","submit_replication":"https://pith.science/pith/XXUSS5MZFH6DKIX4MMCJFZIE3C/action/replication_record"}},"created_at":"2026-07-05T10:39:24.068143+00:00","updated_at":"2026-07-05T10:39:24.068143+00:00"}