{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GEK7KDT2KHCVX7QMPEH7X45YPX","short_pith_number":"pith:GEK7KDT2","schema_version":"1.0","canonical_sha256":"3115f50e7a51c55bfe0c790ffbf3b87dce0cef86b643a502009bacd2b9d4af49","source":{"kind":"arxiv","id":"1708.03949","version":2},"attestation_state":"computed","paper":{"title":"Gradient Methods for Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Hamed Hassani, Mahdi Soltanolkotabi","submitted_at":"2017-08-13T18:20:50Z","abstract_excerpt":"In this paper, we study the problem of maximizing continuous submodular functions that naturally arise in many learning applications such as those involving utility functions in active learning and sensing, matrix approximations and network inference. Despite the apparent lack of convexity in such functions, we prove that stochastic projected gradient methods can provide strong approximation guarantees for maximizing continuous submodular functions with convex constraints. More specifically, we prove that for monotone continuous DR-submodular functions, all fixed points of projected gradient a"},"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":"1708.03949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-13T18:20:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"779ee1e6741bad7f9e963a1b58ca4f9c1f9da8caa27b504e08bf68657db7edc4","abstract_canon_sha256":"99e0b8d41cd3d2077f5942d83f7a9cff51c361e432bb77372bf65770c5cc07d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:59.928531Z","signature_b64":"MA8s7ayTjn0GxdAniHRMn1sWXpHq02624T5ROaDB5fZPZ4dCNoKatN3e/jYYLeHTw8ZlvwikjfXGbj/CTuhHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3115f50e7a51c55bfe0c790ffbf3b87dce0cef86b643a502009bacd2b9d4af49","last_reissued_at":"2026-05-18T00:37:59.927823Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:59.927823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Methods for Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Hamed Hassani, Mahdi Soltanolkotabi","submitted_at":"2017-08-13T18:20:50Z","abstract_excerpt":"In this paper, we study the problem of maximizing continuous submodular functions that naturally arise in many learning applications such as those involving utility functions in active learning and sensing, matrix approximations and network inference. Despite the apparent lack of convexity in such functions, we prove that stochastic projected gradient methods can provide strong approximation guarantees for maximizing continuous submodular functions with convex constraints. More specifically, we prove that for monotone continuous DR-submodular functions, all fixed points of projected gradient a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03949","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":""},"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":"1708.03949","created_at":"2026-05-18T00:37:59.927929+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03949v2","created_at":"2026-05-18T00:37:59.927929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03949","created_at":"2026-05-18T00:37:59.927929+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEK7KDT2KHCV","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEK7KDT2KHCVX7QM","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEK7KDT2","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX","json":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX.json","graph_json":"https://pith.science/api/pith-number/GEK7KDT2KHCVX7QMPEH7X45YPX/graph.json","events_json":"https://pith.science/api/pith-number/GEK7KDT2KHCVX7QMPEH7X45YPX/events.json","paper":"https://pith.science/paper/GEK7KDT2"},"agent_actions":{"view_html":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX","download_json":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX.json","view_paper":"https://pith.science/paper/GEK7KDT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03949&json=true","fetch_graph":"https://pith.science/api/pith-number/GEK7KDT2KHCVX7QMPEH7X45YPX/graph.json","fetch_events":"https://pith.science/api/pith-number/GEK7KDT2KHCVX7QMPEH7X45YPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX/action/storage_attestation","attest_author":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX/action/author_attestation","sign_citation":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX/action/citation_signature","submit_replication":"https://pith.science/pith/GEK7KDT2KHCVX7QMPEH7X45YPX/action/replication_record"}},"created_at":"2026-05-18T00:37:59.927929+00:00","updated_at":"2026-05-18T00:37:59.927929+00:00"}