{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CKQHGS3SHEKETKNNYKWAI6S24","short_pith_number":"pith:5CKQHGS3","schema_version":"1.0","canonical_sha256":"e895039a5b91c8a24d4d6e156023d2d72f086d69948f8dc4eb30a49ff8789585","source":{"kind":"arxiv","id":"2411.00405","version":2},"attestation_state":"computed","paper":{"title":"HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jay Barrett, Kwang-Sung Jun, Tuan Ngo Nguyen","submitted_at":"2024-11-01T07:05:11Z","abstract_excerpt":"We study the problem of estimating the \\emph{value} of the largest mean among K distributions via samples from them (rather than estimating \\emph{which} distribution has the largest mean), which arises from various machine learning tasks including Q-learning and Monte Carlo Tree Search (MCTS). While there have been a few proposed algorithms, their performance analyses have been limited to their biases rather than a precise error metric. In this paper, we propose a novel algorithm called HAVER (Head AVERaging) and analyze its mean squared error. Our analysis reveals that HAVER has a compelling "},"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":"2411.00405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-11-01T07:05:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab7383b531ad7d46b9c7bc43a35b238dd962e5ae066ea98a4e3f02d0a516b869","abstract_canon_sha256":"8c28d79bf3824ef5a093002f9dfca7e200a8e9ad18450d3ce362e66babde6566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:25.470132Z","signature_b64":"E/9p3nGee76GkTUJ11NNoFp4ijghIprpqlhz1+5Q40ppCWOSNEaofmogCA3Bm2QVgYSvyup30Obic8TGfZsgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e895039a5b91c8a24d4d6e156023d2d72f086d69948f8dc4eb30a49ff8789585","last_reissued_at":"2026-07-05T10:55:25.469611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:25.469611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jay Barrett, Kwang-Sung Jun, Tuan Ngo Nguyen","submitted_at":"2024-11-01T07:05:11Z","abstract_excerpt":"We study the problem of estimating the \\emph{value} of the largest mean among K distributions via samples from them (rather than estimating \\emph{which} distribution has the largest mean), which arises from various machine learning tasks including Q-learning and Monte Carlo Tree Search (MCTS). While there have been a few proposed algorithms, their performance analyses have been limited to their biases rather than a precise error metric. In this paper, we propose a novel algorithm called HAVER (Head AVERaging) and analyze its mean squared error. Our analysis reveals that HAVER has a compelling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00405","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/2411.00405/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":"2411.00405","created_at":"2026-07-05T10:55:25.469665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00405v2","created_at":"2026-07-05T10:55:25.469665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00405","created_at":"2026-07-05T10:55:25.469665+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CKQHGS3SHEK","created_at":"2026-07-05T10:55:25.469665+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CKQHGS3SHEKETKN","created_at":"2026-07-05T10:55:25.469665+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CKQHGS3","created_at":"2026-07-05T10:55:25.469665+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/5CKQHGS3SHEKETKNNYKWAI6S24","json":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24.json","graph_json":"https://pith.science/api/pith-number/5CKQHGS3SHEKETKNNYKWAI6S24/graph.json","events_json":"https://pith.science/api/pith-number/5CKQHGS3SHEKETKNNYKWAI6S24/events.json","paper":"https://pith.science/paper/5CKQHGS3"},"agent_actions":{"view_html":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24","download_json":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24.json","view_paper":"https://pith.science/paper/5CKQHGS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00405&json=true","fetch_graph":"https://pith.science/api/pith-number/5CKQHGS3SHEKETKNNYKWAI6S24/graph.json","fetch_events":"https://pith.science/api/pith-number/5CKQHGS3SHEKETKNNYKWAI6S24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24/action/storage_attestation","attest_author":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24/action/author_attestation","sign_citation":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24/action/citation_signature","submit_replication":"https://pith.science/pith/5CKQHGS3SHEKETKNNYKWAI6S24/action/replication_record"}},"created_at":"2026-07-05T10:55:25.469665+00:00","updated_at":"2026-07-05T10:55:25.469665+00:00"}