{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3K35PKG42MRHAEJEOUOLNBO4DN","short_pith_number":"pith:3K35PKG4","schema_version":"1.0","canonical_sha256":"dab7d7a8dcd322701124751cb685dc1b4bc1e57598af2cd640517c7072d82c20","source":{"kind":"arxiv","id":"2007.05670","version":2},"attestation_state":"computed","paper":{"title":"An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Hanrong Ye, Yimin Huang, Yujun Li, Zhenguo Li, Zhihua Zhang","submitted_at":"2020-07-11T03:15:21Z","abstract_excerpt":"The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter op"},"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":"2007.05670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-11T03:15:21Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"a017cc9482d47248a5c20833d2315de782d14a98dc9fef61f495dc6635089841","abstract_canon_sha256":"ae93704de1fec4e72a57865c31011a01416f2f64b67c14894eccda282917c1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:56.614580Z","signature_b64":"KHNXi/E1/iEnZUCAsJIoijJQXLJ/nrzW4XyA5EeKtt75RpKp6YMuHb15OQQpFyosrxkoMQnuaDtBN4RRN6eaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dab7d7a8dcd322701124751cb685dc1b4bc1e57598af2cd640517c7072d82c20","last_reissued_at":"2026-07-05T01:59:56.614127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:56.614127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Hanrong Ye, Yimin Huang, Yujun Li, Zhenguo Li, Zhihua Zhang","submitted_at":"2020-07-11T03:15:21Z","abstract_excerpt":"The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05670","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.05670/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":"2007.05670","created_at":"2026-07-05T01:59:56.614182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.05670v2","created_at":"2026-07-05T01:59:56.614182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05670","created_at":"2026-07-05T01:59:56.614182+00:00"},{"alias_kind":"pith_short_12","alias_value":"3K35PKG42MRH","created_at":"2026-07-05T01:59:56.614182+00:00"},{"alias_kind":"pith_short_16","alias_value":"3K35PKG42MRHAEJE","created_at":"2026-07-05T01:59:56.614182+00:00"},{"alias_kind":"pith_short_8","alias_value":"3K35PKG4","created_at":"2026-07-05T01:59:56.614182+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/3K35PKG42MRHAEJEOUOLNBO4DN","json":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN.json","graph_json":"https://pith.science/api/pith-number/3K35PKG42MRHAEJEOUOLNBO4DN/graph.json","events_json":"https://pith.science/api/pith-number/3K35PKG42MRHAEJEOUOLNBO4DN/events.json","paper":"https://pith.science/paper/3K35PKG4"},"agent_actions":{"view_html":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN","download_json":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN.json","view_paper":"https://pith.science/paper/3K35PKG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.05670&json=true","fetch_graph":"https://pith.science/api/pith-number/3K35PKG42MRHAEJEOUOLNBO4DN/graph.json","fetch_events":"https://pith.science/api/pith-number/3K35PKG42MRHAEJEOUOLNBO4DN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN/action/storage_attestation","attest_author":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN/action/author_attestation","sign_citation":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN/action/citation_signature","submit_replication":"https://pith.science/pith/3K35PKG42MRHAEJEOUOLNBO4DN/action/replication_record"}},"created_at":"2026-07-05T01:59:56.614182+00:00","updated_at":"2026-07-05T01:59:56.614182+00:00"}