{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HZ63SANZSTKFZSKGMTPFYYOJG2","short_pith_number":"pith:HZ63SANZ","schema_version":"1.0","canonical_sha256":"3e7db901b994d45cc94664de5c61c936ad36731b2ff3dfeb86ae80a1043d16c8","source":{"kind":"arxiv","id":"2305.18442","version":1},"attestation_state":"computed","paper":{"title":"Improved Projection-free Online Continuous Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chang Yao, Mingli Song, Yuanyu Wan, Yucheng Liao","submitted_at":"2023-05-29T02:54:31Z","abstract_excerpt":"We investigate the problem of online learning with monotone and continuous DR-submodular reward functions, which has received great attention recently. To efficiently handle this problem, especially in the case with complicated decision sets, previous studies have proposed an efficient projection-free algorithm called Mono-Frank-Wolfe (Mono-FW) using $O(T)$ gradient evaluations and linear optimization steps in total. However, it only attains a $(1-1/e)$-regret bound of $O(T^{4/5})$. In this paper, we propose an improved projection-free algorithm, namely POBGA, which reduces the regret bound to"},"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":"2305.18442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T02:54:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"87b24bf4d98b48bed36b2e384c3188705c75abf775cd264f4a970014d0b71482","abstract_canon_sha256":"9a0fc9b2b08599491ab4fe24fd965cfae27df260d0ba4c8db0b702970b3bb455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:00.959726Z","signature_b64":"yWeZLxDVITzwkvMloFU8KCh47XVIDodJ/rNT2YeVo0gidlb1EYxgpifjsFy/OCDvb6hqcWT7WfuGr7c4mcNUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e7db901b994d45cc94664de5c61c936ad36731b2ff3dfeb86ae80a1043d16c8","last_reissued_at":"2026-07-05T06:15:00.959302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:00.959302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Projection-free Online Continuous Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chang Yao, Mingli Song, Yuanyu Wan, Yucheng Liao","submitted_at":"2023-05-29T02:54:31Z","abstract_excerpt":"We investigate the problem of online learning with monotone and continuous DR-submodular reward functions, which has received great attention recently. To efficiently handle this problem, especially in the case with complicated decision sets, previous studies have proposed an efficient projection-free algorithm called Mono-Frank-Wolfe (Mono-FW) using $O(T)$ gradient evaluations and linear optimization steps in total. However, it only attains a $(1-1/e)$-regret bound of $O(T^{4/5})$. In this paper, we propose an improved projection-free algorithm, namely POBGA, which reduces the regret bound to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18442","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/2305.18442/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":"2305.18442","created_at":"2026-07-05T06:15:00.959359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18442v1","created_at":"2026-07-05T06:15:00.959359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18442","created_at":"2026-07-05T06:15:00.959359+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZ63SANZSTKF","created_at":"2026-07-05T06:15:00.959359+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZ63SANZSTKFZSKG","created_at":"2026-07-05T06:15:00.959359+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZ63SANZ","created_at":"2026-07-05T06:15:00.959359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00523","citing_title":"Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2","json":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2.json","graph_json":"https://pith.science/api/pith-number/HZ63SANZSTKFZSKGMTPFYYOJG2/graph.json","events_json":"https://pith.science/api/pith-number/HZ63SANZSTKFZSKGMTPFYYOJG2/events.json","paper":"https://pith.science/paper/HZ63SANZ"},"agent_actions":{"view_html":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2","download_json":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2.json","view_paper":"https://pith.science/paper/HZ63SANZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18442&json=true","fetch_graph":"https://pith.science/api/pith-number/HZ63SANZSTKFZSKGMTPFYYOJG2/graph.json","fetch_events":"https://pith.science/api/pith-number/HZ63SANZSTKFZSKGMTPFYYOJG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2/action/storage_attestation","attest_author":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2/action/author_attestation","sign_citation":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2/action/citation_signature","submit_replication":"https://pith.science/pith/HZ63SANZSTKFZSKGMTPFYYOJG2/action/replication_record"}},"created_at":"2026-07-05T06:15:00.959359+00:00","updated_at":"2026-07-05T06:15:00.959359+00:00"}