{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YZQLU3K4VXFUGGOQSXPE5HSF2J","short_pith_number":"pith:YZQLU3K4","schema_version":"1.0","canonical_sha256":"c660ba6d5cadcb4319d095de4e9e45d2544c150a7035fb9190670a5af154cdc1","source":{"kind":"arxiv","id":"2112.13487","version":3},"attestation_state":"computed","paper":{"title":"The Statistical Complexity of Interactive Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster, Jian Qian, Sham M. Kakade","submitted_at":"2021-12-27T02:53:44Z","abstract_excerpt":"A fundamental challenge in interactive learning and decision making, ranging from bandit problems to reinforcement learning, is to provide sample-efficient, adaptive learning algorithms that achieve near-optimal regret. This question is analogous to the classical problem of optimal (supervised) statistical learning, where there are well-known complexity measures (e.g., VC dimension and Rademacher complexity) that govern the statistical complexity of learning. However, characterizing the statistical complexity of interactive learning is substantially more challenging due to the adaptive nature "},"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":"2112.13487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T02:53:44Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"857fac3f3b6206f95976c335f1545046b325559dd1de04b88c57e6d358ded31a","abstract_canon_sha256":"df15d7376751ecf37115e9a9ec9f0ed77a5fafba6943b330a1f91db935de4209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:29.290533Z","signature_b64":"PvGuYMK1FntOJzn2MMonanwvsCa7rpUt/lka/zs7vSNfPVzwvEOdjUeHKI3IbkJcysFebcFbR+8ILkbkj69aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c660ba6d5cadcb4319d095de4e9e45d2544c150a7035fb9190670a5af154cdc1","last_reissued_at":"2026-07-05T06:29:29.290100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:29.290100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Statistical Complexity of Interactive Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster, Jian Qian, Sham M. Kakade","submitted_at":"2021-12-27T02:53:44Z","abstract_excerpt":"A fundamental challenge in interactive learning and decision making, ranging from bandit problems to reinforcement learning, is to provide sample-efficient, adaptive learning algorithms that achieve near-optimal regret. This question is analogous to the classical problem of optimal (supervised) statistical learning, where there are well-known complexity measures (e.g., VC dimension and Rademacher complexity) that govern the statistical complexity of learning. However, characterizing the statistical complexity of interactive learning is substantially more challenging due to the adaptive nature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13487","kind":"arxiv","version":3},"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/2112.13487/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":"2112.13487","created_at":"2026-07-05T06:29:29.290155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13487v3","created_at":"2026-07-05T06:29:29.290155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13487","created_at":"2026-07-05T06:29:29.290155+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZQLU3K4VXFU","created_at":"2026-07-05T06:29:29.290155+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZQLU3K4VXFUGGOQ","created_at":"2026-07-05T06:29:29.290155+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZQLU3K4","created_at":"2026-07-05T06:29:29.290155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23096","citing_title":"Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07931","citing_title":"Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11171","citing_title":"Bellman-sufficient Information Complexity","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11171","citing_title":"Bellman-sufficient Information Complexity","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07931","citing_title":"Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02363","citing_title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01382","citing_title":"Efficient Exploration for Iterative Nash Preference Optimization","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30923","citing_title":"Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09200","citing_title":"A Complete Characterization of Learnability for Adversarial Noisy Bandits","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29645","citing_title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21060","citing_title":"On the Sample Complexity of Differentially Private Policy Optimization","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12316","citing_title":"Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09200","citing_title":"A Complete Characterization of Learnability for Adversarial Noisy Bandits","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05791","citing_title":"A Measure-Theoretic Finite-Sample Theory for Adaptive-Data Fitted Q-Iteration","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00393","citing_title":"Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01778","citing_title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07155","citing_title":"Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13966","citing_title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02141","citing_title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J","json":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J.json","graph_json":"https://pith.science/api/pith-number/YZQLU3K4VXFUGGOQSXPE5HSF2J/graph.json","events_json":"https://pith.science/api/pith-number/YZQLU3K4VXFUGGOQSXPE5HSF2J/events.json","paper":"https://pith.science/paper/YZQLU3K4"},"agent_actions":{"view_html":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J","download_json":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J.json","view_paper":"https://pith.science/paper/YZQLU3K4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13487&json=true","fetch_graph":"https://pith.science/api/pith-number/YZQLU3K4VXFUGGOQSXPE5HSF2J/graph.json","fetch_events":"https://pith.science/api/pith-number/YZQLU3K4VXFUGGOQSXPE5HSF2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J/action/storage_attestation","attest_author":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J/action/author_attestation","sign_citation":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J/action/citation_signature","submit_replication":"https://pith.science/pith/YZQLU3K4VXFUGGOQSXPE5HSF2J/action/replication_record"}},"created_at":"2026-07-05T06:29:29.290155+00:00","updated_at":"2026-07-05T06:29:29.290155+00:00"}