{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GNQ4T4VYUTSTDXNHW26R6ZIFCM","short_pith_number":"pith:GNQ4T4VY","schema_version":"1.0","canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","source":{"kind":"arxiv","id":"1709.04073","version":1},"attestation_state":"computed","paper":{"title":"Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandrashekar Lakshminarayanan, Csaba Szepesv\\'ari","submitted_at":"2017-09-12T22:34:09Z","abstract_excerpt":"We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate $\\theta_{*} \\in \\mathbb{R}^d$ (that is an optimum or a fixed point) using noisy data and $O(d)$ updates per iteration. In this paper, we are motivated by the problem (in RL) of policy evaluation from experience replay using the \\emph{temporal difference} (TD) class of learning algorithms that are also LSAs. For LS"},"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":"1709.04073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T22:34:09Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"c90027f8838fe410c5a074a93b1947cbe1d7748cd0bee2998fb8f566ba36a59b","abstract_canon_sha256":"b6022751bf89a0770d358889d8c05c24502889c3c3052e4e30bd84aaeb1c6686"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:15.527195Z","signature_b64":"Omo9TvYJblQsT23UBOYhnSuFdHPMQVZio79E3E1+w8ei5RoMIKmMJM01epa8eIs933f50b3JJyczxRih+JFZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3361c9f2b8a4e531dda7b6bd1f6505133b6d1ce650232d93217294cebac33a03","last_reissued_at":"2026-05-18T00:35:15.526514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:15.526514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandrashekar Lakshminarayanan, Csaba Szepesv\\'ari","submitted_at":"2017-09-12T22:34:09Z","abstract_excerpt":"We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate $\\theta_{*} \\in \\mathbb{R}^d$ (that is an optimum or a fixed point) using noisy data and $O(d)$ updates per iteration. In this paper, we are motivated by the problem (in RL) of policy evaluation from experience replay using the \\emph{temporal difference} (TD) class of learning algorithms that are also LSAs. For LS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04073","kind":"arxiv","version":1},"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":"1709.04073","created_at":"2026-05-18T00:35:15.526620+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04073v1","created_at":"2026-05-18T00:35:15.526620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04073","created_at":"2026-05-18T00:35:15.526620+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNQ4T4VYUTST","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNQ4T4VYUTSTDXNH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNQ4T4VY","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08933","citing_title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM","json":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM.json","graph_json":"https://pith.science/api/pith-number/GNQ4T4VYUTSTDXNHW26R6ZIFCM/graph.json","events_json":"https://pith.science/api/pith-number/GNQ4T4VYUTSTDXNHW26R6ZIFCM/events.json","paper":"https://pith.science/paper/GNQ4T4VY"},"agent_actions":{"view_html":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM","download_json":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM.json","view_paper":"https://pith.science/paper/GNQ4T4VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04073&json=true","fetch_graph":"https://pith.science/api/pith-number/GNQ4T4VYUTSTDXNHW26R6ZIFCM/graph.json","fetch_events":"https://pith.science/api/pith-number/GNQ4T4VYUTSTDXNHW26R6ZIFCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/action/storage_attestation","attest_author":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/action/author_attestation","sign_citation":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/action/citation_signature","submit_replication":"https://pith.science/pith/GNQ4T4VYUTSTDXNHW26R6ZIFCM/action/replication_record"}},"created_at":"2026-05-18T00:35:15.526620+00:00","updated_at":"2026-05-18T00:35:15.526620+00:00"}