{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KRG2XNUJOMGOBUOFLLMQJWNNVZ","short_pith_number":"pith:KRG2XNUJ","schema_version":"1.0","canonical_sha256":"544dabb689730ce0d1c55ad904d9adae4cffb5fd20c0f0cc7be2e67f34c074e7","source":{"kind":"arxiv","id":"2505.14610","version":1},"attestation_state":"computed","paper":{"title":"MMD-Newton Method for Multi-objective Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angel E. Rodriguez-Fernandez, Chenyu Shi, Hao Wang, Oliver Sch\\\"utze","submitted_at":"2025-05-20T16:56:50Z","abstract_excerpt":"Maximum mean discrepancy (MMD) has been widely employed to measure the distance between probability distributions. In this paper, we propose using MMD to solve continuous multi-objective optimization problems (MOPs). For solving MOPs, a common approach is to minimize the distance (e.g., Hausdorff) between a finite approximate set of the Pareto front and a reference set. Viewing these two sets as empirical measures, we propose using MMD to measure the distance between them. To minimize the MMD value, we provide the analytical expression of its gradient and Hessian matrix w.r.t. the search varia"},"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":"2505.14610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T16:56:50Z","cross_cats_sorted":[],"title_canon_sha256":"770ba2707be67bbcd2f97fc99c0e4f1d486945b5552712cd382826af84d27e9b","abstract_canon_sha256":"ca63ba892fe048d5604c0025eda6cc3c1dcf2127bcb93fca2edd4a36ae0f22e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:16.480500Z","signature_b64":"e1AWVOlKhGUW5KlPZVElIrkAiwHccuhsk71azgvrIvTU6Q2WbdJcR9Kb/AD7QSz6FUdrtZMBdTd9Lud35Ow3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"544dabb689730ce0d1c55ad904d9adae4cffb5fd20c0f0cc7be2e67f34c074e7","last_reissued_at":"2026-07-05T11:06:16.479958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:16.479958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMD-Newton Method for Multi-objective Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angel E. Rodriguez-Fernandez, Chenyu Shi, Hao Wang, Oliver Sch\\\"utze","submitted_at":"2025-05-20T16:56:50Z","abstract_excerpt":"Maximum mean discrepancy (MMD) has been widely employed to measure the distance between probability distributions. In this paper, we propose using MMD to solve continuous multi-objective optimization problems (MOPs). For solving MOPs, a common approach is to minimize the distance (e.g., Hausdorff) between a finite approximate set of the Pareto front and a reference set. Viewing these two sets as empirical measures, we propose using MMD to measure the distance between them. To minimize the MMD value, we provide the analytical expression of its gradient and Hessian matrix w.r.t. the search varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14610","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/2505.14610/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":"2505.14610","created_at":"2026-07-05T11:06:16.480024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14610v1","created_at":"2026-07-05T11:06:16.480024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14610","created_at":"2026-07-05T11:06:16.480024+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRG2XNUJOMGO","created_at":"2026-07-05T11:06:16.480024+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRG2XNUJOMGOBUOF","created_at":"2026-07-05T11:06:16.480024+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRG2XNUJ","created_at":"2026-07-05T11:06:16.480024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19383","citing_title":"Quantum Algorithm for Protein Side-Chain Optimisation: Comparing Quantum to Classical Methods","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ","json":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ.json","graph_json":"https://pith.science/api/pith-number/KRG2XNUJOMGOBUOFLLMQJWNNVZ/graph.json","events_json":"https://pith.science/api/pith-number/KRG2XNUJOMGOBUOFLLMQJWNNVZ/events.json","paper":"https://pith.science/paper/KRG2XNUJ"},"agent_actions":{"view_html":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ","download_json":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ.json","view_paper":"https://pith.science/paper/KRG2XNUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14610&json=true","fetch_graph":"https://pith.science/api/pith-number/KRG2XNUJOMGOBUOFLLMQJWNNVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KRG2XNUJOMGOBUOFLLMQJWNNVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ/action/storage_attestation","attest_author":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ/action/author_attestation","sign_citation":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ/action/citation_signature","submit_replication":"https://pith.science/pith/KRG2XNUJOMGOBUOFLLMQJWNNVZ/action/replication_record"}},"created_at":"2026-07-05T11:06:16.480024+00:00","updated_at":"2026-07-05T11:06:16.480024+00:00"}