{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SMCFKVW6XNRVZEY3M56FIWRZLD","short_pith_number":"pith:SMCFKVW6","schema_version":"1.0","canonical_sha256":"93045556debb635c931b677c545a3958e695f1e828947e081011a1aea40119dc","source":{"kind":"arxiv","id":"2105.08285","version":2},"attestation_state":"computed","paper":{"title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Anshumali Shrivastava, Zhao Song, Zhaozhuo Xu","submitted_at":"2021-05-18T05:23:53Z","abstract_excerpt":"We present the first provable Least-Squares Value Iteration (LSVI) algorithms that have runtime complexity sublinear in the number of actions. We formulate the value function estimation procedure in value iteration as an approximate maximum inner product search problem and propose a locality sensitive hashing (LSH) [Indyk and Motwani STOC'98, Andoni and Razenshteyn STOC'15, Andoni, Laarhoven, Razenshteyn and Waingarten SODA'17] type data structure to solve this problem with sublinear time complexity. Moreover, we build the connections between the theory of approximate maximum inner product sea"},"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":"2105.08285","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DS","submitted_at":"2021-05-18T05:23:53Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c9921517318b370006b28a3a282186d1aeaa6b3503a62febd2f086a474247157","abstract_canon_sha256":"cdc240c29dffca574612679704b40639a775eeabf51f6aa1b2188ab7ae236c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:07.793480Z","signature_b64":"VXSHje1So1jY4EC8S1m6ZEI4HlGd5F81pnv+HXAyiuVQ2CfgorBsUs6lssErCRnNmPRo5oN/Br7YToxwFgJ5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93045556debb635c931b677c545a3958e695f1e828947e081011a1aea40119dc","last_reissued_at":"2026-07-05T02:47:07.793011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:07.793011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Anshumali Shrivastava, Zhao Song, Zhaozhuo Xu","submitted_at":"2021-05-18T05:23:53Z","abstract_excerpt":"We present the first provable Least-Squares Value Iteration (LSVI) algorithms that have runtime complexity sublinear in the number of actions. We formulate the value function estimation procedure in value iteration as an approximate maximum inner product search problem and propose a locality sensitive hashing (LSH) [Indyk and Motwani STOC'98, Andoni and Razenshteyn STOC'15, Andoni, Laarhoven, Razenshteyn and Waingarten SODA'17] type data structure to solve this problem with sublinear time complexity. Moreover, we build the connections between the theory of approximate maximum inner product sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08285","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/2105.08285/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":"2105.08285","created_at":"2026-07-05T02:47:07.793065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08285v2","created_at":"2026-07-05T02:47:07.793065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08285","created_at":"2026-07-05T02:47:07.793065+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMCFKVW6XNRV","created_at":"2026-07-05T02:47:07.793065+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMCFKVW6XNRVZEY3","created_at":"2026-07-05T02:47:07.793065+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMCFKVW6","created_at":"2026-07-05T02:47:07.793065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10906","citing_title":"Efficient, Low-Regret, Online Reinforcement Learning for Linear MDPs","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD","json":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD.json","graph_json":"https://pith.science/api/pith-number/SMCFKVW6XNRVZEY3M56FIWRZLD/graph.json","events_json":"https://pith.science/api/pith-number/SMCFKVW6XNRVZEY3M56FIWRZLD/events.json","paper":"https://pith.science/paper/SMCFKVW6"},"agent_actions":{"view_html":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD","download_json":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD.json","view_paper":"https://pith.science/paper/SMCFKVW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08285&json=true","fetch_graph":"https://pith.science/api/pith-number/SMCFKVW6XNRVZEY3M56FIWRZLD/graph.json","fetch_events":"https://pith.science/api/pith-number/SMCFKVW6XNRVZEY3M56FIWRZLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD/action/storage_attestation","attest_author":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD/action/author_attestation","sign_citation":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD/action/citation_signature","submit_replication":"https://pith.science/pith/SMCFKVW6XNRVZEY3M56FIWRZLD/action/replication_record"}},"created_at":"2026-07-05T02:47:07.793065+00:00","updated_at":"2026-07-05T02:47:07.793065+00:00"}