{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E4W7LHOKZPHJDF5DK5NU4UXHDM","short_pith_number":"pith:E4W7LHOK","schema_version":"1.0","canonical_sha256":"272df59dcacbce9197a3575b4e52e71b399560f950b0d3c11afb2083945ab247","source":{"kind":"arxiv","id":"2410.10417","version":1},"attestation_state":"computed","paper":{"title":"A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Timothy M. Hospedales","submitted_at":"2024-10-14T12:10:06Z","abstract_excerpt":"We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more. These problems are often formalized as Bi-Level optimizations (BLO). We introduce a novel perspective by turning a given BLO problem into a stochastic optimization, where the inner loss function becomes a smooth probability distribution, and the outer loss becomes an expected loss over the inner distribution. To solve this stochastic optimization, we adopt Stochastic Gradient Langev"},"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":"2410.10417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T12:10:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3cce989edade6b7a5e90e799e21ec1f015484fa761859d4c4b678b6594f74881","abstract_canon_sha256":"de4c44a7ff7df2e6433eb77bddad3f69bcd95cf1463b39f161adb7ece2362e37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:15.923030Z","signature_b64":"gMo6j+lqWIAjyQ3euEgXuaRuRrpHZmLUMTUjZEJVo79Ats8ssYsWjRFwY22BAaPKSo2Megv7Ame2+R4IekViDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"272df59dcacbce9197a3575b4e52e71b399560f950b0d3c11afb2083945ab247","last_reissued_at":"2026-07-05T09:20:15.922621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:15.922621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Timothy M. Hospedales","submitted_at":"2024-10-14T12:10:06Z","abstract_excerpt":"We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more. These problems are often formalized as Bi-Level optimizations (BLO). We introduce a novel perspective by turning a given BLO problem into a stochastic optimization, where the inner loss function becomes a smooth probability distribution, and the outer loss becomes an expected loss over the inner distribution. To solve this stochastic optimization, we adopt Stochastic Gradient Langev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10417","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/2410.10417/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":"2410.10417","created_at":"2026-07-05T09:20:15.922677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10417v1","created_at":"2026-07-05T09:20:15.922677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10417","created_at":"2026-07-05T09:20:15.922677+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4W7LHOKZPHJ","created_at":"2026-07-05T09:20:15.922677+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4W7LHOKZPHJDF5D","created_at":"2026-07-05T09:20:15.922677+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4W7LHOK","created_at":"2026-07-05T09:20:15.922677+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/E4W7LHOKZPHJDF5DK5NU4UXHDM","json":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM.json","graph_json":"https://pith.science/api/pith-number/E4W7LHOKZPHJDF5DK5NU4UXHDM/graph.json","events_json":"https://pith.science/api/pith-number/E4W7LHOKZPHJDF5DK5NU4UXHDM/events.json","paper":"https://pith.science/paper/E4W7LHOK"},"agent_actions":{"view_html":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM","download_json":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM.json","view_paper":"https://pith.science/paper/E4W7LHOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10417&json=true","fetch_graph":"https://pith.science/api/pith-number/E4W7LHOKZPHJDF5DK5NU4UXHDM/graph.json","fetch_events":"https://pith.science/api/pith-number/E4W7LHOKZPHJDF5DK5NU4UXHDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM/action/storage_attestation","attest_author":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM/action/author_attestation","sign_citation":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM/action/citation_signature","submit_replication":"https://pith.science/pith/E4W7LHOKZPHJDF5DK5NU4UXHDM/action/replication_record"}},"created_at":"2026-07-05T09:20:15.922677+00:00","updated_at":"2026-07-05T09:20:15.922677+00:00"}