{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:X4UPYDYH65LYXXPBHU35KTVQRO","short_pith_number":"pith:X4UPYDYH","schema_version":"1.0","canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","source":{"kind":"arxiv","id":"0912.3995","version":4},"attestation_state":"computed","paper":{"title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Matthias Seeger, Niranjan Srinivas, Sham M. Kakade","submitted_at":"2009-12-21T00:08:19Z","abstract_excerpt":"Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design"},"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":"0912.3995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","cross_cats_sorted":[],"title_canon_sha256":"adb4c26ea869a338a06efb991f4cec5780cfd1b6f5dc4df32c544508cce4df67","abstract_canon_sha256":"e1302309bb547973eb39a67c7707d91f57262f923b480f7c12b1e5faa83c0d93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:24:45.583110Z","signature_b64":"czoBsp+s9gv/zWPPT2cmrDL0UAajnq/jIYrI0jOwhmawp+upAo7ZfktT4tYPNTA6/Mr9PSdSCBICYUFL5lFUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","last_reissued_at":"2026-05-18T02:24:45.582629Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:24:45.582629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Matthias Seeger, Niranjan Srinivas, Sham M. Kakade","submitted_at":"2009-12-21T00:08:19Z","abstract_excerpt":"Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0912.3995","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":"0912.3995","created_at":"2026-05-18T02:24:45.582702+00:00"},{"alias_kind":"arxiv_version","alias_value":"0912.3995v4","created_at":"2026-05-18T02:24:45.582702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0912.3995","created_at":"2026-05-18T02:24:45.582702+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4UPYDYH65LY","created_at":"2026-05-18T12:26:02.257875+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4UPYDYH65LYXXPB","created_at":"2026-05-18T12:26:02.257875+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4UPYDYH","created_at":"2026-05-18T12:26:02.257875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1906.09384","citing_title":"A Bandit Approach to Posterior Dialog Orchestration Under a Budget","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02577","citing_title":"Data-Centric Mixed-Variable Bayesian Optimization For Materials Design","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2404.03099","citing_title":"Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22561","citing_title":"Regret-Based $(\\epsilon,\\delta)$-optimal Stopping Criteria for Bayesian Optimization","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21263","citing_title":"Nonparametric Learning and Earning with One-Point Feedback under Nonstationarity","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17976","citing_title":"Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23351","citing_title":"Laser-Enhanced Contact Optimization in Silicon Photovoltaics: Mechanisms, Reliability, and Predictive Process Design","ref_index":138,"is_internal_anchor":true},{"citing_arxiv_id":"2511.06459","citing_title":"Uncertainty-Aware Offline Data-Driven Multi-Objective Optimization","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08461","citing_title":"Bayesian Optimization of Crossbar-Based Compute-In-Memory System Design for Efficient DNN Inference","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10196","citing_title":"Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10654","citing_title":"Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10230","citing_title":"FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25272","citing_title":"Spectral bandits","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06413","citing_title":"Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07401","citing_title":"Learning myopic mixed-integer nonlinear model predictive control from expert demonstrations","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07863","citing_title":"ADKO: Agentic Decentralized Knowledge Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05859","citing_title":"When Do We Need LLMs? A Diagnostic for Language-Driven Bandits","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05416","citing_title":"Multi-Agent Pathfinding with Non-Unit Integer Edge Costs via Enhanced Conflict-Based Search and Graph Discretization","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14243","citing_title":"Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO","json":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO.json","graph_json":"https://pith.science/api/pith-number/X4UPYDYH65LYXXPBHU35KTVQRO/graph.json","events_json":"https://pith.science/api/pith-number/X4UPYDYH65LYXXPBHU35KTVQRO/events.json","paper":"https://pith.science/paper/X4UPYDYH"},"agent_actions":{"view_html":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO","download_json":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO.json","view_paper":"https://pith.science/paper/X4UPYDYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0912.3995&json=true","fetch_graph":"https://pith.science/api/pith-number/X4UPYDYH65LYXXPBHU35KTVQRO/graph.json","fetch_events":"https://pith.science/api/pith-number/X4UPYDYH65LYXXPBHU35KTVQRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/action/storage_attestation","attest_author":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/action/author_attestation","sign_citation":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/action/citation_signature","submit_replication":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/action/replication_record"}},"created_at":"2026-05-18T02:24:45.582702+00:00","updated_at":"2026-05-18T02:24:45.582702+00:00"}