{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WSXXDESRS2WBBKA25CE5WC5RCZ","short_pith_number":"pith:WSXXDESR","schema_version":"1.0","canonical_sha256":"b4af71925196ac10a81ae889db0bb1167d5a69a0b5442453596df41822abe05b","source":{"kind":"arxiv","id":"2005.09261","version":2},"attestation_state":"computed","paper":{"title":"Adaptive First-and Zeroth-order Methods for Weakly Convex Stochastic Optimization Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Davoud Ataee Tarzanagh, George Michailidis, Parvin Nazari","submitted_at":"2020-05-19T07:44:52Z","abstract_excerpt":"In this paper, we design and analyze a new family of adaptive subgradient methods for solving an important class of weakly convex (possibly nonsmooth) stochastic optimization problems. Adaptive methods that use exponential moving averages of past gradients to update search directions and learning rates have recently attracted a lot of attention for solving optimization problems that arise in machine learning. Nevertheless, their convergence analysis almost exclusively requires smoothness and/or convexity of the objective function. In contrast, we establish non-asymptotic rates of convergence o"},"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":"2005.09261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-19T07:44:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ef192546f589cc33e98e7f2f36e727f166cd27d74c3c4851f08c1cb7f05b88fd","abstract_canon_sha256":"6d15da635fcec751205c2be74568f032bc264e2fb3b7bf35f52b8a10dcec9948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:13.094540Z","signature_b64":"fYlELrc25VJjZLmkrWfow0jt+qCcLLYi8fEzput29OCjvIgkUw1OXAb4oKnMW4StisAvzWE9hJ1yy8eE+ocICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4af71925196ac10a81ae889db0bb1167d5a69a0b5442453596df41822abe05b","last_reissued_at":"2026-07-05T01:05:13.094162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:13.094162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive First-and Zeroth-order Methods for Weakly Convex Stochastic Optimization Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Davoud Ataee Tarzanagh, George Michailidis, Parvin Nazari","submitted_at":"2020-05-19T07:44:52Z","abstract_excerpt":"In this paper, we design and analyze a new family of adaptive subgradient methods for solving an important class of weakly convex (possibly nonsmooth) stochastic optimization problems. Adaptive methods that use exponential moving averages of past gradients to update search directions and learning rates have recently attracted a lot of attention for solving optimization problems that arise in machine learning. Nevertheless, their convergence analysis almost exclusively requires smoothness and/or convexity of the objective function. In contrast, we establish non-asymptotic rates of convergence o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09261","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/2005.09261/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":"2005.09261","created_at":"2026-07-05T01:05:13.094219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.09261v2","created_at":"2026-07-05T01:05:13.094219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09261","created_at":"2026-07-05T01:05:13.094219+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSXXDESRS2WB","created_at":"2026-07-05T01:05:13.094219+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSXXDESRS2WBBKA2","created_at":"2026-07-05T01:05:13.094219+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSXXDESR","created_at":"2026-07-05T01:05:13.094219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01126","citing_title":"Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06016","citing_title":"A Unified Zeroth-Order Proximal Newton-Type Framework for Composite Optimization","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ","json":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ.json","graph_json":"https://pith.science/api/pith-number/WSXXDESRS2WBBKA25CE5WC5RCZ/graph.json","events_json":"https://pith.science/api/pith-number/WSXXDESRS2WBBKA25CE5WC5RCZ/events.json","paper":"https://pith.science/paper/WSXXDESR"},"agent_actions":{"view_html":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ","download_json":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ.json","view_paper":"https://pith.science/paper/WSXXDESR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.09261&json=true","fetch_graph":"https://pith.science/api/pith-number/WSXXDESRS2WBBKA25CE5WC5RCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WSXXDESRS2WBBKA25CE5WC5RCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ/action/storage_attestation","attest_author":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ/action/author_attestation","sign_citation":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ/action/citation_signature","submit_replication":"https://pith.science/pith/WSXXDESRS2WBBKA25CE5WC5RCZ/action/replication_record"}},"created_at":"2026-07-05T01:05:13.094219+00:00","updated_at":"2026-07-05T01:05:13.094219+00:00"}