{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TVRRAMPHRM3FR53WMUZKYPPHIX","short_pith_number":"pith:TVRRAMPH","schema_version":"1.0","canonical_sha256":"9d631031e78b3658f7766532ac3de745f47a18ec0ae97fe1d9b937c3e9baf8ac","source":{"kind":"arxiv","id":"2505.04599","version":1},"attestation_state":"computed","paper":{"title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Michael Crawshaw, Mingrui Liu","submitted_at":"2025-05-07T17:40:12Z","abstract_excerpt":"Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms of problem parameters like the smoothness constants. The complexity guaranteed by such algorithms to find an $\\epsilon$-stationary point may be significantly larger than the optimal complexity of $\\Theta \\left( \\Delta L \\sigma^2 \\epsilon^{-4} \\right)$ achieved by SGD in the $L$-smooth setting, where $\\Delta$ is the initial optimality gap, $\\sigma^2$ is the va"},"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":"2505.04599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:40:12Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"262f72becce754ad8e1f306e2796f090d9f8e22942f421fd81303f09b0de5212","abstract_canon_sha256":"3d381b44913e863fe54ddf05cf8178167e880cba5836471d5e414e11021bd524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:10.464065Z","signature_b64":"2KXESCAD2eHM8l98ylccgWLSqLknry+AnU0Af5f0KsRNMQYmSVcY7W6IdvjzzVrcSV2d8kO5LvCztblhkInZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d631031e78b3658f7766532ac3de745f47a18ec0ae97fe1d9b937c3e9baf8ac","last_reissued_at":"2026-07-05T11:00:10.463512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:10.463512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Michael Crawshaw, Mingrui Liu","submitted_at":"2025-05-07T17:40:12Z","abstract_excerpt":"Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms of problem parameters like the smoothness constants. The complexity guaranteed by such algorithms to find an $\\epsilon$-stationary point may be significantly larger than the optimal complexity of $\\Theta \\left( \\Delta L \\sigma^2 \\epsilon^{-4} \\right)$ achieved by SGD in the $L$-smooth setting, where $\\Delta$ is the initial optimality gap, $\\sigma^2$ is the va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04599","kind":"arxiv","version":1},"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/2505.04599/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":"2505.04599","created_at":"2026-07-05T11:00:10.463576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04599v1","created_at":"2026-07-05T11:00:10.463576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04599","created_at":"2026-07-05T11:00:10.463576+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVRRAMPHRM3F","created_at":"2026-07-05T11:00:10.463576+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVRRAMPHRM3FR53W","created_at":"2026-07-05T11:00:10.463576+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVRRAMPH","created_at":"2026-07-05T11:00:10.463576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08726","citing_title":"Decentralized Stochastic Nonconvex Optimization under the $(L_0,L_1)$-Smoothness","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX","json":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX.json","graph_json":"https://pith.science/api/pith-number/TVRRAMPHRM3FR53WMUZKYPPHIX/graph.json","events_json":"https://pith.science/api/pith-number/TVRRAMPHRM3FR53WMUZKYPPHIX/events.json","paper":"https://pith.science/paper/TVRRAMPH"},"agent_actions":{"view_html":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX","download_json":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX.json","view_paper":"https://pith.science/paper/TVRRAMPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04599&json=true","fetch_graph":"https://pith.science/api/pith-number/TVRRAMPHRM3FR53WMUZKYPPHIX/graph.json","fetch_events":"https://pith.science/api/pith-number/TVRRAMPHRM3FR53WMUZKYPPHIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX/action/storage_attestation","attest_author":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX/action/author_attestation","sign_citation":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX/action/citation_signature","submit_replication":"https://pith.science/pith/TVRRAMPHRM3FR53WMUZKYPPHIX/action/replication_record"}},"created_at":"2026-07-05T11:00:10.463576+00:00","updated_at":"2026-07-05T11:00:10.463576+00:00"}