{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OIGIXMFCI345LMHCOCKPQKCUQJ","short_pith_number":"pith:OIGIXMFC","schema_version":"1.0","canonical_sha256":"720c8bb0a246f9d5b0e27094f82854825527ddf63c89558bd4facf81ea040806","source":{"kind":"arxiv","id":"1809.01465","version":1},"attestation_state":"computed","paper":{"title":"Deep Bilevel Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Paolo Favaro, Simon Jenni","submitted_at":"2018-09-05T12:50:24Z","abstract_excerpt":"We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting. We formulate such principles as a bilevel optimization problem. This formulation allows us to define the optimization of a cost on the validation set subject to another optimization on the training set. The overfitting is controlled by introducing weights on each mini-batch in the training set and by choosing their"},"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":"1809.01465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-05T12:50:24Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b70adcdba58943e3994ea3f645083126557e1cd7a84765d5d580b65a568ecd66","abstract_canon_sha256":"dfb11029a2a435054599e6ad94f16f57b6b915f8372798d15b35a6e1b8ea72c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:27.567039Z","signature_b64":"wdsTMT15+Itlw2R4OvKRHtYaPLaQdriDK0HWBIRvNeLgeyIWk6t8jD+yomDsefX+xtf9IklgxeYpflOVPeQ4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"720c8bb0a246f9d5b0e27094f82854825527ddf63c89558bd4facf81ea040806","last_reissued_at":"2026-05-18T00:06:27.566521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:27.566521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Bilevel Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Paolo Favaro, Simon Jenni","submitted_at":"2018-09-05T12:50:24Z","abstract_excerpt":"We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting. We formulate such principles as a bilevel optimization problem. This formulation allows us to define the optimization of a cost on the validation set subject to another optimization on the training set. The overfitting is controlled by introducing weights on each mini-batch in the training set and by choosing their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01465","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":""},"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":"1809.01465","created_at":"2026-05-18T00:06:27.566602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01465v1","created_at":"2026-05-18T00:06:27.566602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01465","created_at":"2026-05-18T00:06:27.566602+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIGIXMFCI345","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIGIXMFCI345LMHC","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIGIXMFC","created_at":"2026-05-18T12:32:43.782077+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/OIGIXMFCI345LMHCOCKPQKCUQJ","json":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ.json","graph_json":"https://pith.science/api/pith-number/OIGIXMFCI345LMHCOCKPQKCUQJ/graph.json","events_json":"https://pith.science/api/pith-number/OIGIXMFCI345LMHCOCKPQKCUQJ/events.json","paper":"https://pith.science/paper/OIGIXMFC"},"agent_actions":{"view_html":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ","download_json":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ.json","view_paper":"https://pith.science/paper/OIGIXMFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01465&json=true","fetch_graph":"https://pith.science/api/pith-number/OIGIXMFCI345LMHCOCKPQKCUQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OIGIXMFCI345LMHCOCKPQKCUQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ/action/storage_attestation","attest_author":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ/action/author_attestation","sign_citation":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ/action/citation_signature","submit_replication":"https://pith.science/pith/OIGIXMFCI345LMHCOCKPQKCUQJ/action/replication_record"}},"created_at":"2026-05-18T00:06:27.566602+00:00","updated_at":"2026-05-18T00:06:27.566602+00:00"}