{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7RDZLK6LD666GZ6M472532432R","short_pith_number":"pith:7RDZLK6L","schema_version":"1.0","canonical_sha256":"fc4795abcb1fbde367cce7f5ddeb9bd476f67e049a3578d9c0cd5a5a2b6b5407","source":{"kind":"arxiv","id":"1903.09367","version":2},"attestation_state":"computed","paper":{"title":"High-Dimensional Linear Regression via Implicit Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Peng Zhao, Qiao-Chu He, Yun Yang","submitted_at":"2019-03-22T05:56:04Z","abstract_excerpt":"Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined through a discretized gradient dynamic system under overparameterization. We show that under suitable restricted isometry conditions, overparameterization leads to implicit regularization: if we directly apply gradient descent to the residual sum of squares with sufficiently small initial values, then under some proper early stopping rule, the iterates converge to"},"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":"1903.09367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-03-22T05:56:04Z","cross_cats_sorted":["stat.CO","stat.ML","stat.TH"],"title_canon_sha256":"8437839ee3aaf893fd92feab03ef38c3f0937d207c94580459e595ad13bbb31b","abstract_canon_sha256":"ab545b203ee0f06e515580d4e9da60a965b58178840311ee33eb32761048fe80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:13.380308Z","signature_b64":"ECnPMpf6x4yBTyPZx/Xx0V9+d6pyrLy7wv/iIgvnINnAMQjaGNR8YBxNhfb0yZMmVEnbhf38poooH2nVLYhwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc4795abcb1fbde367cce7f5ddeb9bd476f67e049a3578d9c0cd5a5a2b6b5407","last_reissued_at":"2026-07-05T03:56:13.379905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:13.379905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Dimensional Linear Regression via Implicit Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Peng Zhao, Qiao-Chu He, Yun Yang","submitted_at":"2019-03-22T05:56:04Z","abstract_excerpt":"Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined through a discretized gradient dynamic system under overparameterization. We show that under suitable restricted isometry conditions, overparameterization leads to implicit regularization: if we directly apply gradient descent to the residual sum of squares with sufficiently small initial values, then under some proper early stopping rule, the iterates converge to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09367","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/1903.09367/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":"1903.09367","created_at":"2026-07-05T03:56:13.379962+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.09367v2","created_at":"2026-07-05T03:56:13.379962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09367","created_at":"2026-07-05T03:56:13.379962+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RDZLK6LD666","created_at":"2026-07-05T03:56:13.379962+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RDZLK6LD666GZ6M","created_at":"2026-07-05T03:56:13.379962+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RDZLK6L","created_at":"2026-07-05T03:56:13.379962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11436","citing_title":"Implicit Regularization for Multi-label Feature Selection","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R","json":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R.json","graph_json":"https://pith.science/api/pith-number/7RDZLK6LD666GZ6M472532432R/graph.json","events_json":"https://pith.science/api/pith-number/7RDZLK6LD666GZ6M472532432R/events.json","paper":"https://pith.science/paper/7RDZLK6L"},"agent_actions":{"view_html":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R","download_json":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R.json","view_paper":"https://pith.science/paper/7RDZLK6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.09367&json=true","fetch_graph":"https://pith.science/api/pith-number/7RDZLK6LD666GZ6M472532432R/graph.json","fetch_events":"https://pith.science/api/pith-number/7RDZLK6LD666GZ6M472532432R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R/action/storage_attestation","attest_author":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R/action/author_attestation","sign_citation":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R/action/citation_signature","submit_replication":"https://pith.science/pith/7RDZLK6LD666GZ6M472532432R/action/replication_record"}},"created_at":"2026-07-05T03:56:13.379962+00:00","updated_at":"2026-07-05T03:56:13.379962+00:00"}