{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XDWCS5JQGCUGURWYJOIDDPOH3D","short_pith_number":"pith:XDWCS5JQ","schema_version":"1.0","canonical_sha256":"b8ec29753030a86a46d84b9031bdc7d8c8ddbd3512717007223840a6a35203de","source":{"kind":"arxiv","id":"2011.11150","version":4},"attestation_state":"computed","paper":{"title":"On the Convergence of Continuous Constrained Optimization for Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignavier Ng, Kun Zhang, Nan Rosemary Ke, S\\'ebastien Lachapelle, Simon Lacoste-Julien","submitted_at":"2020-11-23T00:29:37Z","abstract_excerpt":"Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity. The constrained problem is solved using the augmented Lagrangian method (ALM) which is often preferred to the quadratic penalty method (QPM) by virtue of its standard convergence result that does not require the penalty coefficient to go to infinity, hence avoiding ill-conditioning. However, the convergence properties of these methods for structure learning, including whether they are guaranteed to return a DAG soluti"},"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":"2011.11150","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:29:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9971a3c4a1c23247af3bda0d9b55a745e3882a17bc121ab8063b2fa7196edd07","abstract_canon_sha256":"9b10822d7d0def72e5b52fda19ca7d77ec3e26555402c603aeece4593760083b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:48.161975Z","signature_b64":"l4rVIqd1hkEwuiWgOWbXaeXsGCzRtxwRfQn5i6sc9CQv7N+2jSJIDVuVbG5AzsVkDvqu37A2uV8Fr02WImkhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ec29753030a86a46d84b9031bdc7d8c8ddbd3512717007223840a6a35203de","last_reissued_at":"2026-07-05T04:12:48.161633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:48.161633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of Continuous Constrained Optimization for Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignavier Ng, Kun Zhang, Nan Rosemary Ke, S\\'ebastien Lachapelle, Simon Lacoste-Julien","submitted_at":"2020-11-23T00:29:37Z","abstract_excerpt":"Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity. The constrained problem is solved using the augmented Lagrangian method (ALM) which is often preferred to the quadratic penalty method (QPM) by virtue of its standard convergence result that does not require the penalty coefficient to go to infinity, hence avoiding ill-conditioning. However, the convergence properties of these methods for structure learning, including whether they are guaranteed to return a DAG soluti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11150","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/2011.11150/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":"2011.11150","created_at":"2026-07-05T04:12:48.161687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11150v4","created_at":"2026-07-05T04:12:48.161687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11150","created_at":"2026-07-05T04:12:48.161687+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDWCS5JQGCUG","created_at":"2026-07-05T04:12:48.161687+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDWCS5JQGCUGURWY","created_at":"2026-07-05T04:12:48.161687+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDWCS5JQ","created_at":"2026-07-05T04:12:48.161687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14126","citing_title":"Toward Temporal Causal Representation Learning with Tensor Decomposition","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D","json":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D.json","graph_json":"https://pith.science/api/pith-number/XDWCS5JQGCUGURWYJOIDDPOH3D/graph.json","events_json":"https://pith.science/api/pith-number/XDWCS5JQGCUGURWYJOIDDPOH3D/events.json","paper":"https://pith.science/paper/XDWCS5JQ"},"agent_actions":{"view_html":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D","download_json":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D.json","view_paper":"https://pith.science/paper/XDWCS5JQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11150&json=true","fetch_graph":"https://pith.science/api/pith-number/XDWCS5JQGCUGURWYJOIDDPOH3D/graph.json","fetch_events":"https://pith.science/api/pith-number/XDWCS5JQGCUGURWYJOIDDPOH3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D/action/storage_attestation","attest_author":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D/action/author_attestation","sign_citation":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D/action/citation_signature","submit_replication":"https://pith.science/pith/XDWCS5JQGCUGURWYJOIDDPOH3D/action/replication_record"}},"created_at":"2026-07-05T04:12:48.161687+00:00","updated_at":"2026-07-05T04:12:48.161687+00:00"}