{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YISHPUZHOKBOTIGVFTVSV4GIMW","short_pith_number":"pith:YISHPUZH","schema_version":"1.0","canonical_sha256":"c22477d3277282e9a0d52ceb2af0c865817131587286b23773d5052d386cc1cd","source":{"kind":"arxiv","id":"1806.04910","version":2},"attestation_state":"computed","paper":{"title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Franceschi, Massimilano Pontil, Paolo Frasconi, Riccardo Grazzi, Saverio Salzo","submitted_at":"2018-06-13T09:21:42Z","abstract_excerpt":"We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel problem can be solved by taking into explicit account the optimization dynamics for the inner objective. Depending on the specific setting, the outer variables take either the meaning of hyperparameters in a supervised learning problem or parameters of a meta-learner. We provide sufficient conditions under which solutions of the approximate problem converge to those of the exact problem. We instantiate our approach f"},"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":"1806.04910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-13T09:21:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df7d0323167136043c40c94a9a79daba6883eba6a4fb99e0d0eb781991169ea3","abstract_canon_sha256":"95c79b6eec235068028daae7af0dd17fe41b8fa451290a4ab6e9ed70537051e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:46.604105Z","signature_b64":"8It2SfDZAO72QRhiSsGO+QkCZDmFWT4UKLJeeHltI4TgMwq10whVRScKIibchiBPK7OX9D6eh+y46Ptarx91Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22477d3277282e9a0d52ceb2af0c865817131587286b23773d5052d386cc1cd","last_reissued_at":"2026-05-18T00:11:46.603417Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:46.603417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Franceschi, Massimilano Pontil, Paolo Frasconi, Riccardo Grazzi, Saverio Salzo","submitted_at":"2018-06-13T09:21:42Z","abstract_excerpt":"We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel problem can be solved by taking into explicit account the optimization dynamics for the inner objective. Depending on the specific setting, the outer variables take either the meaning of hyperparameters in a supervised learning problem or parameters of a meta-learner. We provide sufficient conditions under which solutions of the approximate problem converge to those of the exact problem. We instantiate our approach f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04910","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":""},"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":"1806.04910","created_at":"2026-05-18T00:11:46.603516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04910v2","created_at":"2026-05-18T00:11:46.603516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04910","created_at":"2026-05-18T00:11:46.603516+00:00"},{"alias_kind":"pith_short_12","alias_value":"YISHPUZHOKBO","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YISHPUZHOKBOTIGV","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YISHPUZH","created_at":"2026-05-18T12:33:04.347982+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/YISHPUZHOKBOTIGVFTVSV4GIMW","json":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW.json","graph_json":"https://pith.science/api/pith-number/YISHPUZHOKBOTIGVFTVSV4GIMW/graph.json","events_json":"https://pith.science/api/pith-number/YISHPUZHOKBOTIGVFTVSV4GIMW/events.json","paper":"https://pith.science/paper/YISHPUZH"},"agent_actions":{"view_html":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW","download_json":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW.json","view_paper":"https://pith.science/paper/YISHPUZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04910&json=true","fetch_graph":"https://pith.science/api/pith-number/YISHPUZHOKBOTIGVFTVSV4GIMW/graph.json","fetch_events":"https://pith.science/api/pith-number/YISHPUZHOKBOTIGVFTVSV4GIMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW/action/storage_attestation","attest_author":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW/action/author_attestation","sign_citation":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW/action/citation_signature","submit_replication":"https://pith.science/pith/YISHPUZHOKBOTIGVFTVSV4GIMW/action/replication_record"}},"created_at":"2026-05-18T00:11:46.603516+00:00","updated_at":"2026-05-18T00:11:46.603516+00:00"}