{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:B7H6RI4ERAGVLGQCQS3IHEV3BF","short_pith_number":"pith:B7H6RI4E","schema_version":"1.0","canonical_sha256":"0fcfe8a384880d559a0284b68392bb096de7f3d95fda2d94bf399925f4766182","source":{"kind":"arxiv","id":"1603.06560","version":4},"attestation_state":"computed","paper":{"title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Ameet Talwalkar, Giulia DeSalvo, Kevin Jamieson, Lisha Li","submitted_at":"2016-03-21T19:51:04Z","abstract_excerpt":"Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation and early-stopping. We formulate hyperparameter optimization as a pure-exploration non-stochastic infinite-armed bandit problem where a predefined resource like iterations, data samples, or features is allocated to randomly sampled configurations. We introduce a novel algorithm, Hyperband, for this framework and analyze its theo"},"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":"1603.06560","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-21T19:51:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9809af9e26f081523230495e1d087a52412ee91ce1fe0c94fb429ae7c2de8aa1","abstract_canon_sha256":"32fc58616bcdaefef32d2deec5dbf30bbf1aba34c3669172c6166a12f502ee08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:58.808305Z","signature_b64":"cVPaCaaTtVk10wwkLNc14PZIv90xWUz2MvMOIu21A4dFcVAMVcic7d2v4Fk+WpErpBF84Soaslb9vv4rWNpaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fcfe8a384880d559a0284b68392bb096de7f3d95fda2d94bf399925f4766182","last_reissued_at":"2026-05-18T00:12:58.807664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:58.807664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Ameet Talwalkar, Giulia DeSalvo, Kevin Jamieson, Lisha Li","submitted_at":"2016-03-21T19:51:04Z","abstract_excerpt":"Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation and early-stopping. We formulate hyperparameter optimization as a pure-exploration non-stochastic infinite-armed bandit problem where a predefined resource like iterations, data samples, or features is allocated to randomly sampled configurations. We introduce a novel algorithm, Hyperband, for this framework and analyze its theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06560","kind":"arxiv","version":4},"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":"1603.06560","created_at":"2026-05-18T00:12:58.807745+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.06560v4","created_at":"2026-05-18T00:12:58.807745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06560","created_at":"2026-05-18T00:12:58.807745+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7H6RI4ERAGV","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7H6RI4ERAGVLGQC","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7H6RI4E","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09084","citing_title":"Joint Detection of Malicious Domains and Infected Clients","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15484","citing_title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1910.09700","citing_title":"Quantifying the Carbon Emissions of Machine Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00313","citing_title":"Beyond Structure: Revolutionising Materials Discovery via AI-Driven Synthesis Protocol-Property Relationships","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17842","citing_title":"QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14860","citing_title":"Best of both worlds: Stochastic & adversarial best-arm identification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF","json":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF.json","graph_json":"https://pith.science/api/pith-number/B7H6RI4ERAGVLGQCQS3IHEV3BF/graph.json","events_json":"https://pith.science/api/pith-number/B7H6RI4ERAGVLGQCQS3IHEV3BF/events.json","paper":"https://pith.science/paper/B7H6RI4E"},"agent_actions":{"view_html":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF","download_json":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF.json","view_paper":"https://pith.science/paper/B7H6RI4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.06560&json=true","fetch_graph":"https://pith.science/api/pith-number/B7H6RI4ERAGVLGQCQS3IHEV3BF/graph.json","fetch_events":"https://pith.science/api/pith-number/B7H6RI4ERAGVLGQCQS3IHEV3BF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF/action/storage_attestation","attest_author":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF/action/author_attestation","sign_citation":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF/action/citation_signature","submit_replication":"https://pith.science/pith/B7H6RI4ERAGVLGQCQS3IHEV3BF/action/replication_record"}},"created_at":"2026-05-18T00:12:58.807745+00:00","updated_at":"2026-05-18T00:12:58.807745+00:00"}