{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CBJ4NXZ66RTQ5462MKK447TEQW","short_pith_number":"pith:CBJ4NXZ6","schema_version":"1.0","canonical_sha256":"1053c6df3ef4670ef3da6295ce7e6485a25de69ff88898de436f5411a6705b76","source":{"kind":"arxiv","id":"2508.06884","version":2},"attestation_state":"computed","paper":{"title":"Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alexander Tyurin","submitted_at":"2025-08-09T08:28:06Z","abstract_excerpt":"We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $\\ell$-smoothness condition $||\\nabla^{2}f(x)|| \\le \\ell\\left(||\\nabla f(x)||\\right),$ which generalizes the $L$-smoothness and $(L_{0},L_{1})$-smoothness. While accelerated gradient descent AGD is known to reach the optimal complexity $O(\\sqrt{L} R / \\sqrt{\\varepsilon})$ under $L$-smoothness, where $\\varepsilon$ is an error tolerance and $R$ is the distance between a starting and an optimal point, existing extensions to $\\ell$-smoothness either incur extra dependence on the initia"},"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":"2508.06884","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-08-09T08:28:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"79c139e67862cabbf98d31a7a79896cbc70a6aa425b1733dfb8721deb97f7fec","abstract_canon_sha256":"1fcdf5fb80fd9e18677465459cec39365d8ed893d6978406a5b58b0ba7a1799d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:45.146731Z","signature_b64":"QW5Mwvs/ayKqfGcCtL4V/gVDqA0eE82wodCWpbV4JIdWktK+zldTFIrgq1zRbNH5ZYU0Ew+FfCnisbXOFAaFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1053c6df3ef4670ef3da6295ce7e6485a25de69ff88898de436f5411a6705b76","last_reissued_at":"2026-05-22T01:03:45.145810Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:45.145810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alexander Tyurin","submitted_at":"2025-08-09T08:28:06Z","abstract_excerpt":"We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $\\ell$-smoothness condition $||\\nabla^{2}f(x)|| \\le \\ell\\left(||\\nabla f(x)||\\right),$ which generalizes the $L$-smoothness and $(L_{0},L_{1})$-smoothness. While accelerated gradient descent AGD is known to reach the optimal complexity $O(\\sqrt{L} R / \\sqrt{\\varepsilon})$ under $L$-smoothness, where $\\varepsilon$ is an error tolerance and $R$ is the distance between a starting and an optimal point, existing extensions to $\\ell$-smoothness either incur extra dependence on the initia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06884","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/2508.06884/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":"2508.06884","created_at":"2026-05-22T01:03:45.145955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06884v2","created_at":"2026-05-22T01:03:45.145955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06884","created_at":"2026-05-22T01:03:45.145955+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBJ4NXZ66RTQ","created_at":"2026-05-22T01:03:45.145955+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBJ4NXZ66RTQ5462","created_at":"2026-05-22T01:03:45.145955+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBJ4NXZ6","created_at":"2026-05-22T01:03:45.145955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04884","citing_title":"A Few Accelerated Algorithms for Convex Optimization under $(H_0,H_1)$-Smoothness","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW","json":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW.json","graph_json":"https://pith.science/api/pith-number/CBJ4NXZ66RTQ5462MKK447TEQW/graph.json","events_json":"https://pith.science/api/pith-number/CBJ4NXZ66RTQ5462MKK447TEQW/events.json","paper":"https://pith.science/paper/CBJ4NXZ6"},"agent_actions":{"view_html":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW","download_json":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW.json","view_paper":"https://pith.science/paper/CBJ4NXZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06884&json=true","fetch_graph":"https://pith.science/api/pith-number/CBJ4NXZ66RTQ5462MKK447TEQW/graph.json","fetch_events":"https://pith.science/api/pith-number/CBJ4NXZ66RTQ5462MKK447TEQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW/action/storage_attestation","attest_author":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW/action/author_attestation","sign_citation":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW/action/citation_signature","submit_replication":"https://pith.science/pith/CBJ4NXZ66RTQ5462MKK447TEQW/action/replication_record"}},"created_at":"2026-05-22T01:03:45.145955+00:00","updated_at":"2026-05-22T01:03:45.145955+00:00"}