{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KYTRPHNVDT5MUERTTNLIDLTP2X","short_pith_number":"pith:KYTRPHNV","schema_version":"1.0","canonical_sha256":"5627179db51cfaca12339b5681ae6fd5f97ca05bb512137b3d46445a377847f1","source":{"kind":"arxiv","id":"1503.05087","version":2},"attestation_state":"computed","paper":{"title":"Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"G\\'abor Bart\\'ok, Gergely Neu","submitted_at":"2015-03-17T15:26:15Z","abstract_excerpt":"We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations. Our new method, called Geometric Resampling (GR), is described and analyzed in the context of online combinatorial optimization under semi-bandit feedback, where a learner sequentially selects its actions from a combinatorial decision set so as to minimize its cumulative loss. In particular, we show that the well-known Follow-the-Perturbed-Leader (FPL) prediction method coupled with Geometric Resampling yields the fi"},"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":"1503.05087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-17T15:26:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13068ca6e8f77e081cbe6868fe00c11bf08b5f9933a95c268325361a2f6d77fb","abstract_canon_sha256":"06610271fe111cb0e2cfc718b43c05d1fedbf4150f1601f80face567b75c8e08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:29.278542Z","signature_b64":"tYiZ8VadNGlgCThksGqVFKGOKA0j0RUpRucP5C6lEjUXfiabM+OdD6KG28h+L8buazC8yC1nYM3JStMuUbIbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5627179db51cfaca12339b5681ae6fd5f97ca05bb512137b3d46445a377847f1","last_reissued_at":"2026-05-18T01:06:29.278079Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:29.278079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"G\\'abor Bart\\'ok, Gergely Neu","submitted_at":"2015-03-17T15:26:15Z","abstract_excerpt":"We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations. Our new method, called Geometric Resampling (GR), is described and analyzed in the context of online combinatorial optimization under semi-bandit feedback, where a learner sequentially selects its actions from a combinatorial decision set so as to minimize its cumulative loss. In particular, we show that the well-known Follow-the-Perturbed-Leader (FPL) prediction method coupled with Geometric Resampling yields the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05087","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":""},"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":"1503.05087","created_at":"2026-05-18T01:06:29.278146+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.05087v2","created_at":"2026-05-18T01:06:29.278146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05087","created_at":"2026-05-18T01:06:29.278146+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYTRPHNVDT5M","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYTRPHNVDT5MUERT","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYTRPHNV","created_at":"2026-05-18T12:29:29.992203+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/KYTRPHNVDT5MUERTTNLIDLTP2X","json":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X.json","graph_json":"https://pith.science/api/pith-number/KYTRPHNVDT5MUERTTNLIDLTP2X/graph.json","events_json":"https://pith.science/api/pith-number/KYTRPHNVDT5MUERTTNLIDLTP2X/events.json","paper":"https://pith.science/paper/KYTRPHNV"},"agent_actions":{"view_html":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X","download_json":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X.json","view_paper":"https://pith.science/paper/KYTRPHNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.05087&json=true","fetch_graph":"https://pith.science/api/pith-number/KYTRPHNVDT5MUERTTNLIDLTP2X/graph.json","fetch_events":"https://pith.science/api/pith-number/KYTRPHNVDT5MUERTTNLIDLTP2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X/action/storage_attestation","attest_author":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X/action/author_attestation","sign_citation":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X/action/citation_signature","submit_replication":"https://pith.science/pith/KYTRPHNVDT5MUERTTNLIDLTP2X/action/replication_record"}},"created_at":"2026-05-18T01:06:29.278146+00:00","updated_at":"2026-05-18T01:06:29.278146+00:00"}