{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OZZTEVMFFRCDWO5KUQY63RI2QK","short_pith_number":"pith:OZZTEVMF","schema_version":"1.0","canonical_sha256":"76733255852c443b3baaa431edc51a82be001452e0ee9451837fbf070547699f","source":{"kind":"arxiv","id":"2107.02371","version":4},"attestation_state":"computed","paper":{"title":"Weighted Gaussian Process Bandits for Non-stationary Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ambuj Tewari, Baekjin Kim, Ness Shroff, Xingyu Zhou, Yuntian Deng","submitted_at":"2021-07-06T03:37:33Z","abstract_excerpt":"In this paper, we consider the Gaussian process (GP) bandit optimization problem in a non-stationary environment. To capture external changes, the black-box function is allowed to be time-varying within a reproducing kernel Hilbert space (RKHS). To this end, we develop WGP-UCB, a novel UCB-type algorithm based on weighted Gaussian process regression. A key challenge is how to cope with infinite-dimensional feature maps. To that end, we leverage kernel approximation techniques to prove a sublinear regret bound, which is the first (frequentist) sublinear regret guarantee on weighted time-varying"},"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":"2107.02371","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T03:37:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6636dcb8b605d0bf5503926b8fc02bc9cd56eeeb29fb2f67103afe4eec31e599","abstract_canon_sha256":"6fea270d2b5e41533a9516257aa18facaa89b779b4d8aad9956fd1f338fab6d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:57.801661Z","signature_b64":"+IBqqJcsb/lLZqbFYwEjLQBYd9OwpGTmB+oUhj1R5h1XcVCKlvMBAu4SgvLf+/GEacZqDIaofSbMxQy85Ve6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76733255852c443b3baaa431edc51a82be001452e0ee9451837fbf070547699f","last_reissued_at":"2026-07-05T04:08:57.801224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:57.801224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Gaussian Process Bandits for Non-stationary Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ambuj Tewari, Baekjin Kim, Ness Shroff, Xingyu Zhou, Yuntian Deng","submitted_at":"2021-07-06T03:37:33Z","abstract_excerpt":"In this paper, we consider the Gaussian process (GP) bandit optimization problem in a non-stationary environment. To capture external changes, the black-box function is allowed to be time-varying within a reproducing kernel Hilbert space (RKHS). To this end, we develop WGP-UCB, a novel UCB-type algorithm based on weighted Gaussian process regression. A key challenge is how to cope with infinite-dimensional feature maps. To that end, we leverage kernel approximation techniques to prove a sublinear regret bound, which is the first (frequentist) sublinear regret guarantee on weighted time-varying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02371","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.02371/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":"2107.02371","created_at":"2026-07-05T04:08:57.801278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02371v4","created_at":"2026-07-05T04:08:57.801278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02371","created_at":"2026-07-05T04:08:57.801278+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZZTEVMFFRCD","created_at":"2026-07-05T04:08:57.801278+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZZTEVMFFRCDWO5K","created_at":"2026-07-05T04:08:57.801278+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZZTEVMF","created_at":"2026-07-05T04:08:57.801278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13005","citing_title":"Geometry-Aware Multi-Armed Bandits for Antenna Beam Selection on Spheres, Tori, $\\SO(3)$, and Reconfigurable Intelligent Surfaces","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK","json":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK.json","graph_json":"https://pith.science/api/pith-number/OZZTEVMFFRCDWO5KUQY63RI2QK/graph.json","events_json":"https://pith.science/api/pith-number/OZZTEVMFFRCDWO5KUQY63RI2QK/events.json","paper":"https://pith.science/paper/OZZTEVMF"},"agent_actions":{"view_html":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK","download_json":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK.json","view_paper":"https://pith.science/paper/OZZTEVMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02371&json=true","fetch_graph":"https://pith.science/api/pith-number/OZZTEVMFFRCDWO5KUQY63RI2QK/graph.json","fetch_events":"https://pith.science/api/pith-number/OZZTEVMFFRCDWO5KUQY63RI2QK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK/action/storage_attestation","attest_author":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK/action/author_attestation","sign_citation":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK/action/citation_signature","submit_replication":"https://pith.science/pith/OZZTEVMFFRCDWO5KUQY63RI2QK/action/replication_record"}},"created_at":"2026-07-05T04:08:57.801278+00:00","updated_at":"2026-07-05T04:08:57.801278+00:00"}