{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JH4FZFWAQUAGKVXDRDSX7OTZLG","short_pith_number":"pith:JH4FZFWA","schema_version":"1.0","canonical_sha256":"49f85c96c085006556e388e57fba7959961bb521acfac0e14fcc9868d2ea37c9","source":{"kind":"arxiv","id":"1810.10667","version":2},"attestation_state":"computed","paper":{"title":"Truncated Back-propagation for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirreza Shaban, Byron Boots, Ching-An Cheng, Nathan Hatch","submitted_at":"2018-10-25T00:49:36Z","abstract_excerpt":"Bilevel optimization has been recently revisited for designing and analyzing algorithms in hyperparameter tuning and meta learning tasks. However, due to its nested structure, evaluating exact gradients for high-dimensional problems is computationally challenging. One heuristic to circumvent this difficulty is to use the approximate gradient given by performing truncated back-propagation through the iterative optimization procedure that solves the lower-level problem. Although promising empirical performance has been reported, its theoretical properties are still unclear. In this paper, we ana"},"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":"1810.10667","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T00:49:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ed5c41fe86e0983d1d2dffe94b2ee0d53d189245e2f38c4c91f1bd8b9edbc687","abstract_canon_sha256":"97175cf0b74eba8efbd0051b7caabb73375a5c1954521cc806fa820b340fbe24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.237876Z","signature_b64":"x9CR4axaQrty08uqTLfoPpEiDXWbLrLIcYBT5zbVOuV/D/cKpyE5iIokhFJ1pseGa1nRUB9OkqGT2JEKmsIQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f85c96c085006556e388e57fba7959961bb521acfac0e14fcc9868d2ea37c9","last_reissued_at":"2026-05-17T23:49:17.237236Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.237236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Truncated Back-propagation for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirreza Shaban, Byron Boots, Ching-An Cheng, Nathan Hatch","submitted_at":"2018-10-25T00:49:36Z","abstract_excerpt":"Bilevel optimization has been recently revisited for designing and analyzing algorithms in hyperparameter tuning and meta learning tasks. However, due to its nested structure, evaluating exact gradients for high-dimensional problems is computationally challenging. One heuristic to circumvent this difficulty is to use the approximate gradient given by performing truncated back-propagation through the iterative optimization procedure that solves the lower-level problem. Although promising empirical performance has been reported, its theoretical properties are still unclear. In this paper, we ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10667","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":"1810.10667","created_at":"2026-05-17T23:49:17.237336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10667v2","created_at":"2026-05-17T23:49:17.237336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10667","created_at":"2026-05-17T23:49:17.237336+00:00"},{"alias_kind":"pith_short_12","alias_value":"JH4FZFWAQUAG","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JH4FZFWAQUAGKVXD","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JH4FZFWA","created_at":"2026-05-18T12:32:31.084164+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/JH4FZFWAQUAGKVXDRDSX7OTZLG","json":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG.json","graph_json":"https://pith.science/api/pith-number/JH4FZFWAQUAGKVXDRDSX7OTZLG/graph.json","events_json":"https://pith.science/api/pith-number/JH4FZFWAQUAGKVXDRDSX7OTZLG/events.json","paper":"https://pith.science/paper/JH4FZFWA"},"agent_actions":{"view_html":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG","download_json":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG.json","view_paper":"https://pith.science/paper/JH4FZFWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10667&json=true","fetch_graph":"https://pith.science/api/pith-number/JH4FZFWAQUAGKVXDRDSX7OTZLG/graph.json","fetch_events":"https://pith.science/api/pith-number/JH4FZFWAQUAGKVXDRDSX7OTZLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG/action/storage_attestation","attest_author":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG/action/author_attestation","sign_citation":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG/action/citation_signature","submit_replication":"https://pith.science/pith/JH4FZFWAQUAGKVXDRDSX7OTZLG/action/replication_record"}},"created_at":"2026-05-17T23:49:17.237336+00:00","updated_at":"2026-05-17T23:49:17.237336+00:00"}