{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SZZS3QMORNNZVV6F2Z4HZZUDOD","short_pith_number":"pith:SZZS3QMO","schema_version":"1.0","canonical_sha256":"96732dc18e8b5b9ad7c5d6787ce68370f37dea886b5d1972d9051d4897ec3e02","source":{"kind":"arxiv","id":"1807.01774","version":1},"attestation_state":"computed","paper":{"title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Frank Hutter, Stefan Falkner","submitted_at":"2018-07-04T20:59:35Z","abstract_excerpt":"Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-based configuration evaluation approaches based on random search lack guidance and do not converge to the best configurations as quickly. Here, we propose to combine the benefits of both Bayesian optimization and bandit-based methods, in order to achieve the best of both worlds: strong anytime performance and fast convergence to optimal configuratio"},"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":"1807.01774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T20:59:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7caf53937a08a8844d0047f2b27ca0732af3e33bedb0eb6d24c73bb9d995ec77","abstract_canon_sha256":"4dd61bb760a3526fb3c391842371eed1b392acbe3d62b84fdbe22edf10949e75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:28.668716Z","signature_b64":"cc2WoU/mKYbmGkYeUkQPS6rkWjfBfzH44SvYNw3tx1saydUF/aEzPUZb15W6C1kJQFPsscLBIZBgmStCqxjEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96732dc18e8b5b9ad7c5d6787ce68370f37dea886b5d1972d9051d4897ec3e02","last_reissued_at":"2026-05-18T00:11:28.668094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:28.668094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Frank Hutter, Stefan Falkner","submitted_at":"2018-07-04T20:59:35Z","abstract_excerpt":"Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-based configuration evaluation approaches based on random search lack guidance and do not converge to the best configurations as quickly. Here, we propose to combine the benefits of both Bayesian optimization and bandit-based methods, in order to achieve the best of both worlds: strong anytime performance and fast convergence to optimal configuratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01774","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":"1807.01774","created_at":"2026-05-18T00:11:28.668180+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01774v1","created_at":"2026-05-18T00:11:28.668180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01774","created_at":"2026-05-18T00:11:28.668180+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZZS3QMORNNZ","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZZS3QMORNNZVV6F","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZZS3QMO","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.11527","citing_title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1910.09700","citing_title":"Quantifying the Carbon Emissions of Machine Learning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09022","citing_title":"Inferring identified hadron production in $pp$ collisions with physics-informed machine learning at the LHC","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17842","citing_title":"QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD","json":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD.json","graph_json":"https://pith.science/api/pith-number/SZZS3QMORNNZVV6F2Z4HZZUDOD/graph.json","events_json":"https://pith.science/api/pith-number/SZZS3QMORNNZVV6F2Z4HZZUDOD/events.json","paper":"https://pith.science/paper/SZZS3QMO"},"agent_actions":{"view_html":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD","download_json":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD.json","view_paper":"https://pith.science/paper/SZZS3QMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01774&json=true","fetch_graph":"https://pith.science/api/pith-number/SZZS3QMORNNZVV6F2Z4HZZUDOD/graph.json","fetch_events":"https://pith.science/api/pith-number/SZZS3QMORNNZVV6F2Z4HZZUDOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD/action/storage_attestation","attest_author":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD/action/author_attestation","sign_citation":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD/action/citation_signature","submit_replication":"https://pith.science/pith/SZZS3QMORNNZVV6F2Z4HZZUDOD/action/replication_record"}},"created_at":"2026-05-18T00:11:28.668180+00:00","updated_at":"2026-05-18T00:11:28.668180+00:00"}