{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z7Y5MLVVZY7LE2B2IB2MDEYYV5","short_pith_number":"pith:Z7Y5MLVV","schema_version":"1.0","canonical_sha256":"cff1d62eb5ce3eb2683a4074c19318af614e054fafe3ed0fd344bce85c06cbf4","source":{"kind":"arxiv","id":"1802.04332","version":4},"attestation_state":"computed","paper":{"title":"Entropy Penalized Semidefinite Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jakub Marecek, Martin Takac, Mikhail Krechetov, Yury Maximov","submitted_at":"2018-02-12T19:53:19Z","abstract_excerpt":"Low-rank methods for semidefinite programming (SDP) have gained a lot of interest recently, especially in machine learning applications. Their analysis often involves determinant-based or Schatten-norm penalties, which are hard to implement in practice due to high computational efforts. In this paper, we propose Entropy Penalized Semi-definite programming (EP-SDP) which provides a unified framework for a wide class of penalty functions used in practice to promote a low-rank solution. We show that EP-SDP problems admit efficient numerical algorithm having (almost) linear time complexity of the "},"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":"1802.04332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-12T19:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"f3a934cbf950cad626fe652f53cdb47c398c4cd10601ae45df4f643783cac3d8","abstract_canon_sha256":"b9be09b7fbf9f831efefdbbece0723deaaf4aa1b0480350cc9144707a0013a9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:36.252287Z","signature_b64":"CCGeWm+9negQiCAQuvbJ59ZDtqouiWtr0AN+0WpY+AHidrEbnM4ICYFqePkjWYz3ECwr3Sru1GvziHn+eNLfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff1d62eb5ce3eb2683a4074c19318af614e054fafe3ed0fd344bce85c06cbf4","last_reissued_at":"2026-07-05T03:37:36.251895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:36.251895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy Penalized Semidefinite Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jakub Marecek, Martin Takac, Mikhail Krechetov, Yury Maximov","submitted_at":"2018-02-12T19:53:19Z","abstract_excerpt":"Low-rank methods for semidefinite programming (SDP) have gained a lot of interest recently, especially in machine learning applications. Their analysis often involves determinant-based or Schatten-norm penalties, which are hard to implement in practice due to high computational efforts. In this paper, we propose Entropy Penalized Semi-definite programming (EP-SDP) which provides a unified framework for a wide class of penalty functions used in practice to promote a low-rank solution. We show that EP-SDP problems admit efficient numerical algorithm having (almost) linear time complexity of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04332","kind":"arxiv","version":4},"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/1802.04332/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":"1802.04332","created_at":"2026-07-05T03:37:36.251953+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04332v4","created_at":"2026-07-05T03:37:36.251953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04332","created_at":"2026-07-05T03:37:36.251953+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7Y5MLVVZY7L","created_at":"2026-07-05T03:37:36.251953+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7Y5MLVVZY7LE2B2","created_at":"2026-07-05T03:37:36.251953+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7Y5MLVV","created_at":"2026-07-05T03:37:36.251953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09711","citing_title":"Non-Euclidean dual gradient ascent for entropically regularized linear and semidefinite programming","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5","json":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5.json","graph_json":"https://pith.science/api/pith-number/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/graph.json","events_json":"https://pith.science/api/pith-number/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/events.json","paper":"https://pith.science/paper/Z7Y5MLVV"},"agent_actions":{"view_html":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5","download_json":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5.json","view_paper":"https://pith.science/paper/Z7Y5MLVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04332&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/action/storage_attestation","attest_author":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/action/author_attestation","sign_citation":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/action/citation_signature","submit_replication":"https://pith.science/pith/Z7Y5MLVVZY7LE2B2IB2MDEYYV5/action/replication_record"}},"created_at":"2026-07-05T03:37:36.251953+00:00","updated_at":"2026-07-05T03:37:36.251953+00:00"}