{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T5L43APTPESRG74PCJFJWIYOBX","short_pith_number":"pith:T5L43APT","schema_version":"1.0","canonical_sha256":"9f57cd81f37925137f8f124a9b230e0dc8be0cf74d8dad938307f5c1803254ba","source":{"kind":"arxiv","id":"2501.12189","version":2},"attestation_state":"computed","paper":{"title":"MirrorCBO: A consensus-based optimization method in the spirit of mirror descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dohyeon Kim, Franca Hoffmann, Leon Bungert, Tim Roith","submitted_at":"2025-01-21T14:50:19Z","abstract_excerpt":"In this work we propose MirrorCBO, a consensus-based optimization (CBO) method which generalizes standard CBO in the same way that mirror descent generalizes gradient descent. For this we apply the CBO methodology to a swarm of dual particles and retain the primal particle positions by applying the inverse of the mirror map, which we parametrize as the subdifferential of a strongly convex function $\\phi$. In this way, we combine the advantages of a derivative-free non-convex optimization algorithm with those of mirror descent. As a special case, the method extends CBO to optimization problems "},"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":"2501.12189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-01-21T14:50:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8456cfd919d40988a8e991ee909ef1dff1332ddf3346135cff321f68b7250b45","abstract_canon_sha256":"4bde6645db8674cec3816f310794219ce5f2ab9d4851456365b0bcbad89c0216"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:30.304287Z","signature_b64":"TZQ2Sj8cP94V9xrzhA1j3xzU4ps1Bvd5xHGf3EBLgKq6udZBNISiJcWrrT2bvh/QqM4X0Dzx9ELhS3T7CyR2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f57cd81f37925137f8f124a9b230e0dc8be0cf74d8dad938307f5c1803254ba","last_reissued_at":"2026-06-02T01:03:30.303845Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:30.303845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MirrorCBO: A consensus-based optimization method in the spirit of mirror descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dohyeon Kim, Franca Hoffmann, Leon Bungert, Tim Roith","submitted_at":"2025-01-21T14:50:19Z","abstract_excerpt":"In this work we propose MirrorCBO, a consensus-based optimization (CBO) method which generalizes standard CBO in the same way that mirror descent generalizes gradient descent. For this we apply the CBO methodology to a swarm of dual particles and retain the primal particle positions by applying the inverse of the mirror map, which we parametrize as the subdifferential of a strongly convex function $\\phi$. In this way, we combine the advantages of a derivative-free non-convex optimization algorithm with those of mirror descent. As a special case, the method extends CBO to optimization problems "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12189","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.12189/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":"2501.12189","created_at":"2026-06-02T01:03:30.303903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12189v2","created_at":"2026-06-02T01:03:30.303903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12189","created_at":"2026-06-02T01:03:30.303903+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5L43APTPESR","created_at":"2026-06-02T01:03:30.303903+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5L43APTPESRG74P","created_at":"2026-06-02T01:03:30.303903+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5L43APT","created_at":"2026-06-02T01:03:30.303903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.09789","citing_title":"ProxiCBO: A Provably Convergent Consensus-Based Method for Composite Optimization","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX","json":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX.json","graph_json":"https://pith.science/api/pith-number/T5L43APTPESRG74PCJFJWIYOBX/graph.json","events_json":"https://pith.science/api/pith-number/T5L43APTPESRG74PCJFJWIYOBX/events.json","paper":"https://pith.science/paper/T5L43APT"},"agent_actions":{"view_html":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX","download_json":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX.json","view_paper":"https://pith.science/paper/T5L43APT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12189&json=true","fetch_graph":"https://pith.science/api/pith-number/T5L43APTPESRG74PCJFJWIYOBX/graph.json","fetch_events":"https://pith.science/api/pith-number/T5L43APTPESRG74PCJFJWIYOBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX/action/storage_attestation","attest_author":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX/action/author_attestation","sign_citation":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX/action/citation_signature","submit_replication":"https://pith.science/pith/T5L43APTPESRG74PCJFJWIYOBX/action/replication_record"}},"created_at":"2026-06-02T01:03:30.303903+00:00","updated_at":"2026-06-02T01:03:30.303903+00:00"}