{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZLWBYQPR3TWASHBDNECYHEW3U7","short_pith_number":"pith:ZLWBYQPR","schema_version":"1.0","canonical_sha256":"caec1c41f1dcec091c2369058392dba7fcc484aeac648c7d82160108a7349b14","source":{"kind":"arxiv","id":"2305.14161","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Subgradient Method: Complexity and Convergence Beyond Lipschitz Continuity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Anthony Man-Cho So, Daoli Zhu, Lei Zhao, Xiao Li","submitted_at":"2023-05-23T15:26:36Z","abstract_excerpt":"The subgradient method is one of the most fundamental algorithmic schemes for nonsmooth optimization. The existing complexity and convergence results for this method are mainly derived for Lipschitz continuous objective functions. In this work, we first extend the typical iteration complexity results for the subgradient method to cover non-Lipschitz convex and weakly convex minimization. Specifically, for the convex case, we can drive the suboptimality gap to below $\\varepsilon$ in $\\mathcal{O}( \\varepsilon^{-2} )$ iterations; for the weakly convex case, we can drive the gradient norm of the M"},"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":"2305.14161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-23T15:26:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0358e2dc293643eaf576333a6d08f441b814e2269956ae10b19376132dc33ddc","abstract_canon_sha256":"c8ebddd5edd099683fb7605ba2b926267e754bfe2e45fb9a1c74f198f5572a7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:45.300285Z","signature_b64":"Om20Qk6ygUZzMfpwxvlhkMh7feWH7DAR5GvwYDiYXQ5y1w1Ei0g2Pmkm8s+bR/+AgmR5woXqb0Y4Iw/nABgnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caec1c41f1dcec091c2369058392dba7fcc484aeac648c7d82160108a7349b14","last_reissued_at":"2026-07-05T09:28:45.299826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:45.299826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Subgradient Method: Complexity and Convergence Beyond Lipschitz Continuity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Anthony Man-Cho So, Daoli Zhu, Lei Zhao, Xiao Li","submitted_at":"2023-05-23T15:26:36Z","abstract_excerpt":"The subgradient method is one of the most fundamental algorithmic schemes for nonsmooth optimization. The existing complexity and convergence results for this method are mainly derived for Lipschitz continuous objective functions. In this work, we first extend the typical iteration complexity results for the subgradient method to cover non-Lipschitz convex and weakly convex minimization. Specifically, for the convex case, we can drive the suboptimality gap to below $\\varepsilon$ in $\\mathcal{O}( \\varepsilon^{-2} )$ iterations; for the weakly convex case, we can drive the gradient norm of the M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14161","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/2305.14161/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":"2305.14161","created_at":"2026-07-05T09:28:45.299879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14161v2","created_at":"2026-07-05T09:28:45.299879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14161","created_at":"2026-07-05T09:28:45.299879+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLWBYQPR3TWA","created_at":"2026-07-05T09:28:45.299879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLWBYQPR3TWASHBD","created_at":"2026-07-05T09:28:45.299879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLWBYQPR","created_at":"2026-07-05T09:28:45.299879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14345","citing_title":"Convergence of difference inclusions via a diameter criterion","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7","json":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7.json","graph_json":"https://pith.science/api/pith-number/ZLWBYQPR3TWASHBDNECYHEW3U7/graph.json","events_json":"https://pith.science/api/pith-number/ZLWBYQPR3TWASHBDNECYHEW3U7/events.json","paper":"https://pith.science/paper/ZLWBYQPR"},"agent_actions":{"view_html":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7","download_json":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7.json","view_paper":"https://pith.science/paper/ZLWBYQPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14161&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLWBYQPR3TWASHBDNECYHEW3U7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLWBYQPR3TWASHBDNECYHEW3U7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7/action/storage_attestation","attest_author":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7/action/author_attestation","sign_citation":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7/action/citation_signature","submit_replication":"https://pith.science/pith/ZLWBYQPR3TWASHBDNECYHEW3U7/action/replication_record"}},"created_at":"2026-07-05T09:28:45.299879+00:00","updated_at":"2026-07-05T09:28:45.299879+00:00"}