{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:D2IJHSW4LAR4IRCNP2HUE3T4LT","short_pith_number":"pith:D2IJHSW4","schema_version":"1.0","canonical_sha256":"1e9093cadc5823c4444d7e8f426e7c5cd738e050e6b1684cce0cff111e01abc4","source":{"kind":"arxiv","id":"1712.04332","version":1},"attestation_state":"computed","paper":{"title":"Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuang Wang, Jonathan Mattingly, Yue M. Lu","submitted_at":"2017-12-08T00:20:18Z","abstract_excerpt":"We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numeric"},"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":"1712.04332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T00:20:18Z","cross_cats_sorted":["cs.IT","math.IT","math.PR","stat.ML"],"title_canon_sha256":"5b7520a36a755232d782c3f4c0654d3ef2e4dee4984169ecd92740bbd23e9f57","abstract_canon_sha256":"4ad1d0e8f44ed546b47838684c0ececa52b952a9a8dca2637088ec89a6b6c70c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:08.335223Z","signature_b64":"GEGYsCiqDKZspswM08jNXa3YDO+xUYj9Di0TVWq4npNtxWTd9tuD+gURFfsHbutH+5T2YvVznRM9Qfp0qDI2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e9093cadc5823c4444d7e8f426e7c5cd738e050e6b1684cce0cff111e01abc4","last_reissued_at":"2026-05-18T00:28:08.334482Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:08.334482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuang Wang, Jonathan Mattingly, Yue M. Lu","submitted_at":"2017-12-08T00:20:18Z","abstract_excerpt":"We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numeric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04332","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":"1712.04332","created_at":"2026-05-18T00:28:08.334608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.04332v1","created_at":"2026-05-18T00:28:08.334608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04332","created_at":"2026-05-18T00:28:08.334608+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2IJHSW4LAR4","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2IJHSW4LAR4IRCN","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2IJHSW4","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08552","citing_title":"Learnability and Competition in High-Dimensional Multi-Component ICA","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT","json":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT.json","graph_json":"https://pith.science/api/pith-number/D2IJHSW4LAR4IRCNP2HUE3T4LT/graph.json","events_json":"https://pith.science/api/pith-number/D2IJHSW4LAR4IRCNP2HUE3T4LT/events.json","paper":"https://pith.science/paper/D2IJHSW4"},"agent_actions":{"view_html":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT","download_json":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT.json","view_paper":"https://pith.science/paper/D2IJHSW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.04332&json=true","fetch_graph":"https://pith.science/api/pith-number/D2IJHSW4LAR4IRCNP2HUE3T4LT/graph.json","fetch_events":"https://pith.science/api/pith-number/D2IJHSW4LAR4IRCNP2HUE3T4LT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT/action/storage_attestation","attest_author":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT/action/author_attestation","sign_citation":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT/action/citation_signature","submit_replication":"https://pith.science/pith/D2IJHSW4LAR4IRCNP2HUE3T4LT/action/replication_record"}},"created_at":"2026-05-18T00:28:08.334608+00:00","updated_at":"2026-05-18T00:28:08.334608+00:00"}