{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G3LOWZQP6JPZ5EKJ5SV5MKDWST","short_pith_number":"pith:G3LOWZQP","schema_version":"1.0","canonical_sha256":"36d6eb660ff25f9e9149ecabd6287694de4e0f47c82639d168fb6c77fe14e54f","source":{"kind":"arxiv","id":"2608.12704","version":1},"attestation_state":"computed","paper":{"title":"Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Feihu Huang, Yicong Jiang","submitted_at":"2026-08-13T01:37:49Z","abstract_excerpt":"Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works have been begun to study the multi-objective bilevel optimization, the proposed methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) to solve the multi-objective bilevel learning pr"},"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":"2608.12704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-08-13T01:37:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ea9030f7790b0a199b14fbf66a20ee028bf126147e1fc671b6422db599c36e2","abstract_canon_sha256":"491c89a9364d7ce6c872b952dd2439b0feb47409d62439faa8d7079ddd82be7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:46:57.875592Z","signature_b64":"ZgDrlcrhVTr7O5q4ksoBNRQyTdpVUq8ZuSg2ANU1sA3RmcjFzuJpTFlp/qKA9qO9/aTbU9vX6dDv3oDAV852Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d6eb660ff25f9e9149ecabd6287694de4e0f47c82639d168fb6c77fe14e54f","last_reissued_at":"2026-08-14T00:46:57.847357Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:46:57.847357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Feihu Huang, Yicong Jiang","submitted_at":"2026-08-13T01:37:49Z","abstract_excerpt":"Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works have been begun to study the multi-objective bilevel optimization, the proposed methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) to solve the multi-objective bilevel learning pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12704","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/2608.12704/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":"2608.12704","created_at":"2026-08-14T00:46:57.864958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12704v1","created_at":"2026-08-14T00:46:57.864958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12704","created_at":"2026-08-14T00:46:57.864958+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3LOWZQP6JPZ","created_at":"2026-08-14T00:46:57.864958+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3LOWZQP6JPZ5EKJ","created_at":"2026-08-14T00:46:57.864958+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3LOWZQP","created_at":"2026-08-14T00:46:57.864958+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/G3LOWZQP6JPZ5EKJ5SV5MKDWST","json":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST.json","graph_json":"https://pith.science/api/pith-number/G3LOWZQP6JPZ5EKJ5SV5MKDWST/graph.json","events_json":"https://pith.science/api/pith-number/G3LOWZQP6JPZ5EKJ5SV5MKDWST/events.json","paper":"https://pith.science/paper/G3LOWZQP"},"agent_actions":{"view_html":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST","download_json":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST.json","view_paper":"https://pith.science/paper/G3LOWZQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12704&json=true","fetch_graph":"https://pith.science/api/pith-number/G3LOWZQP6JPZ5EKJ5SV5MKDWST/graph.json","fetch_events":"https://pith.science/api/pith-number/G3LOWZQP6JPZ5EKJ5SV5MKDWST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST/action/storage_attestation","attest_author":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST/action/author_attestation","sign_citation":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST/action/citation_signature","submit_replication":"https://pith.science/pith/G3LOWZQP6JPZ5EKJ5SV5MKDWST/action/replication_record"}},"created_at":"2026-08-14T00:46:57.864958+00:00","updated_at":"2026-08-14T00:46:57.864958+00:00"}