{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BPGJUH4HRDD46ZW47QHHNKYSTR","short_pith_number":"pith:BPGJUH4H","schema_version":"1.0","canonical_sha256":"0bcc9a1f8788c7cf66dcfc0e76ab129c4ab5c04272a8455e3e97ecf054c4a1dd","source":{"kind":"arxiv","id":"2203.11860","version":3},"attestation_state":"computed","paper":{"title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"C. Daniel Freeman, James Harrison, Jascha Sohl-Dickstein, Luke Metz, Niru Maheswaranathan","submitted_at":"2022-03-22T16:36:36Z","abstract_excerpt":"Optimization plays a costly and crucial role in developing machine learning systems. In learned optimizers, the few hyperparameters of commonly used hand-designed optimizers, e.g. Adam or SGD, are replaced with flexible parametric functions. The parameters of these functions are then optimized so that the resulting learned optimizer minimizes a target loss on a chosen class of models. Learned optimizers can both reduce the number of required training steps and improve the final test loss. However, they can be expensive to train, and once trained can be expensive to use due to computational and"},"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":"2203.11860","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-22T16:36:36Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"5164ff5c145fee65cc6b968f81b3dea7a915889c6bc879f1ef00c157825cbce6","abstract_canon_sha256":"e60bff0d780c8557e4c32e628114841c33b38a1158052ca9762bceb52951e8ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:52.690068Z","signature_b64":"Jb5bhexg8Hj9hi7UrmQCw8ZH3tY4PA33ts8sAA7+VjucwJ3KtnnXtYjrOmJ8ohPNU/sRUeITBeRw/qnqgIuKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bcc9a1f8788c7cf66dcfc0e76ab129c4ab5c04272a8455e3e97ecf054c4a1dd","last_reissued_at":"2026-07-05T04:40:52.689631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:52.689631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"C. Daniel Freeman, James Harrison, Jascha Sohl-Dickstein, Luke Metz, Niru Maheswaranathan","submitted_at":"2022-03-22T16:36:36Z","abstract_excerpt":"Optimization plays a costly and crucial role in developing machine learning systems. In learned optimizers, the few hyperparameters of commonly used hand-designed optimizers, e.g. Adam or SGD, are replaced with flexible parametric functions. The parameters of these functions are then optimized so that the resulting learned optimizer minimizes a target loss on a chosen class of models. Learned optimizers can both reduce the number of required training steps and improve the final test loss. However, they can be expensive to train, and once trained can be expensive to use due to computational and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11860","kind":"arxiv","version":3},"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/2203.11860/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":"2203.11860","created_at":"2026-07-05T04:40:52.689688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11860v3","created_at":"2026-07-05T04:40:52.689688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11860","created_at":"2026-07-05T04:40:52.689688+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPGJUH4HRDD4","created_at":"2026-07-05T04:40:52.689688+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPGJUH4HRDD46ZW4","created_at":"2026-07-05T04:40:52.689688+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPGJUH4H","created_at":"2026-07-05T04:40:52.689688+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/BPGJUH4HRDD46ZW47QHHNKYSTR","json":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR.json","graph_json":"https://pith.science/api/pith-number/BPGJUH4HRDD46ZW47QHHNKYSTR/graph.json","events_json":"https://pith.science/api/pith-number/BPGJUH4HRDD46ZW47QHHNKYSTR/events.json","paper":"https://pith.science/paper/BPGJUH4H"},"agent_actions":{"view_html":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR","download_json":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR.json","view_paper":"https://pith.science/paper/BPGJUH4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11860&json=true","fetch_graph":"https://pith.science/api/pith-number/BPGJUH4HRDD46ZW47QHHNKYSTR/graph.json","fetch_events":"https://pith.science/api/pith-number/BPGJUH4HRDD46ZW47QHHNKYSTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR/action/storage_attestation","attest_author":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR/action/author_attestation","sign_citation":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR/action/citation_signature","submit_replication":"https://pith.science/pith/BPGJUH4HRDD46ZW47QHHNKYSTR/action/replication_record"}},"created_at":"2026-07-05T04:40:52.689688+00:00","updated_at":"2026-07-05T04:40:52.689688+00:00"}