{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JXTMIVFCIAW4B2NJ6ZBESOCTWL","short_pith_number":"pith:JXTMIVFC","schema_version":"1.0","canonical_sha256":"4de6c454a2402dc0e9a9f642493853b2cfa468ee1a3a0c2b3a9f13c52b858109","source":{"kind":"arxiv","id":"1911.02590","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Jonathan Lorraine, Paul Vicol","submitted_at":"2019-11-06T19:04:16Z","abstract_excerpt":"We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT and differentiating through optimization, motivating our algorithm. We use the proposed approach to train modern network architectures with millions of weights and millions of hyper-parameters. For example, we learn a data-augmentation network - where every weight is a hyperparameter tuned for validation performance - outputting augmented training examples. Jo"},"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":"1911.02590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-06T19:04:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d62d840538724489538adca9bab2e5927105f4d4bf7030e455335d2dc1b0cf15","abstract_canon_sha256":"b949c6061ab88eb34bf598f9f43cee0e7c7cfea1de44d627a38609cfd6a2001e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:39.536653Z","signature_b64":"QyqBQ0leSS28Rh3Hr/sgAF2HfYDevuVQYy3zdJRm2U/C4Xx6mQMsNgTMLpHZTGStFakrS4oog1nAM0qMFhsJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de6c454a2402dc0e9a9f642493853b2cfa468ee1a3a0c2b3a9f13c52b858109","last_reissued_at":"2026-07-05T00:17:39.536159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:39.536159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Jonathan Lorraine, Paul Vicol","submitted_at":"2019-11-06T19:04:16Z","abstract_excerpt":"We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT and differentiating through optimization, motivating our algorithm. We use the proposed approach to train modern network architectures with millions of weights and millions of hyper-parameters. For example, we learn a data-augmentation network - where every weight is a hyperparameter tuned for validation performance - outputting augmented training examples. Jo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02590","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/1911.02590/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":"1911.02590","created_at":"2026-07-05T00:17:39.536218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.02590v1","created_at":"2026-07-05T00:17:39.536218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02590","created_at":"2026-07-05T00:17:39.536218+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXTMIVFCIAW4","created_at":"2026-07-05T00:17:39.536218+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXTMIVFCIAW4B2NJ","created_at":"2026-07-05T00:17:39.536218+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXTMIVFC","created_at":"2026-07-05T00:17:39.536218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12718","citing_title":"CHAL: Council of Hierarchical Agentic Language","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL","json":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL.json","graph_json":"https://pith.science/api/pith-number/JXTMIVFCIAW4B2NJ6ZBESOCTWL/graph.json","events_json":"https://pith.science/api/pith-number/JXTMIVFCIAW4B2NJ6ZBESOCTWL/events.json","paper":"https://pith.science/paper/JXTMIVFC"},"agent_actions":{"view_html":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL","download_json":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL.json","view_paper":"https://pith.science/paper/JXTMIVFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.02590&json=true","fetch_graph":"https://pith.science/api/pith-number/JXTMIVFCIAW4B2NJ6ZBESOCTWL/graph.json","fetch_events":"https://pith.science/api/pith-number/JXTMIVFCIAW4B2NJ6ZBESOCTWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL/action/storage_attestation","attest_author":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL/action/author_attestation","sign_citation":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL/action/citation_signature","submit_replication":"https://pith.science/pith/JXTMIVFCIAW4B2NJ6ZBESOCTWL/action/replication_record"}},"created_at":"2026-07-05T00:17:39.536218+00:00","updated_at":"2026-07-05T00:17:39.536218+00:00"}