{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M5TFNOJRGSWRRY3AEV42DKJ5GW","short_pith_number":"pith:M5TFNOJR","schema_version":"1.0","canonical_sha256":"676656b93134ad18e3602579a1a93d3584d2f996b1584595492cda9880982ac3","source":{"kind":"arxiv","id":"2208.05127","version":3},"attestation_state":"computed","paper":{"title":"Projection-Free Non-Smooth Convex Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kamiar Asgari, Michael J. Neely","submitted_at":"2022-08-10T03:47:35Z","abstract_excerpt":"In this paper, we provide a sub-gradient based algorithm to solve general constrained convex optimization without taking projections onto the domain set. The well studied Frank-Wolfe type algorithms also avoid projections. However, they are only designed to handle smooth objective functions. The proposed algorithm treats both smooth and non-smooth problems and achieves an $O(1/\\sqrt{T})$ convergence rate (which matches existing lower bounds). The algorithm yields similar performance in expectation when the deterministic sub-gradients are replaced by stochastic sub-gradients. Thus, the proposed"},"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":"2208.05127","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-08-10T03:47:35Z","cross_cats_sorted":[],"title_canon_sha256":"f6dc4e58e04288b1424af6f887c86fb3c12cb5d6a44aef29e150679589cc95f7","abstract_canon_sha256":"004f01bea060b3a2697fb8f5a29105515999d884c6cd4afadb3eb373a59e43c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:03.884117Z","signature_b64":"+w1Q1zUWiW4y8MVNiZrE96x94JIndOlDlfd/zlPOgk0aPUn8Z1QK6cwo++x2ulkcquzNB0kTHaO9BueJ+wyPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"676656b93134ad18e3602579a1a93d3584d2f996b1584595492cda9880982ac3","last_reissued_at":"2026-07-05T06:21:03.883746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:03.883746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projection-Free Non-Smooth Convex Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kamiar Asgari, Michael J. Neely","submitted_at":"2022-08-10T03:47:35Z","abstract_excerpt":"In this paper, we provide a sub-gradient based algorithm to solve general constrained convex optimization without taking projections onto the domain set. The well studied Frank-Wolfe type algorithms also avoid projections. However, they are only designed to handle smooth objective functions. The proposed algorithm treats both smooth and non-smooth problems and achieves an $O(1/\\sqrt{T})$ convergence rate (which matches existing lower bounds). The algorithm yields similar performance in expectation when the deterministic sub-gradients are replaced by stochastic sub-gradients. Thus, the proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05127","kind":"arxiv","version":3},"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/2208.05127/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":"2208.05127","created_at":"2026-07-05T06:21:03.883807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.05127v3","created_at":"2026-07-05T06:21:03.883807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05127","created_at":"2026-07-05T06:21:03.883807+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5TFNOJRGSWR","created_at":"2026-07-05T06:21:03.883807+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5TFNOJRGSWRRY3A","created_at":"2026-07-05T06:21:03.883807+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5TFNOJR","created_at":"2026-07-05T06:21:03.883807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15926","citing_title":"An Absolute-Error Proximal Bundle Method through the Lens of Frank-Wolf","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW","json":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW.json","graph_json":"https://pith.science/api/pith-number/M5TFNOJRGSWRRY3AEV42DKJ5GW/graph.json","events_json":"https://pith.science/api/pith-number/M5TFNOJRGSWRRY3AEV42DKJ5GW/events.json","paper":"https://pith.science/paper/M5TFNOJR"},"agent_actions":{"view_html":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW","download_json":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW.json","view_paper":"https://pith.science/paper/M5TFNOJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.05127&json=true","fetch_graph":"https://pith.science/api/pith-number/M5TFNOJRGSWRRY3AEV42DKJ5GW/graph.json","fetch_events":"https://pith.science/api/pith-number/M5TFNOJRGSWRRY3AEV42DKJ5GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW/action/storage_attestation","attest_author":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW/action/author_attestation","sign_citation":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW/action/citation_signature","submit_replication":"https://pith.science/pith/M5TFNOJRGSWRRY3AEV42DKJ5GW/action/replication_record"}},"created_at":"2026-07-05T06:21:03.883807+00:00","updated_at":"2026-07-05T06:21:03.883807+00:00"}