{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IDAOT2LVF47MBTL5W2LFOIADCR","short_pith_number":"pith:IDAOT2LV","schema_version":"1.0","canonical_sha256":"40c0e9e9752f3ec0cd7db696572003147945ff14ed07f6bd1ff97017cc2deb2b","source":{"kind":"arxiv","id":"2305.11055","version":2},"attestation_state":"computed","paper":{"title":"Small noise analysis for Tikhonov and RKHS regularizations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fei Lu, Quanjun Lang","submitted_at":"2023-05-18T15:50:33Z","abstract_excerpt":"Regularization plays a pivotal role in ill-posed machine learning and inverse problems. However, the fundamental comparative analysis of various regularization norms remains open. We establish a small noise analysis framework to assess the effects of norms in Tikhonov and RKHS regularizations, in the context of ill-posed linear inverse problems with Gaussian noise. This framework studies the convergence rates of regularized estimators in the small noise limit and reveals the potential instability of the conventional L2-regularizer. We solve such instability by proposing an innovative class of "},"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":"2305.11055","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-18T15:50:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1048a8bba9f7ab689d0b5c9f891704d19eb9e57bcf43287f443eca794888be51","abstract_canon_sha256":"d276fa5fe74a0e6a91390648fc81a25fd9b294e316c0b01fbe17792a59072b33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:39.388757Z","signature_b64":"uY4/eXBvqMyQXTDPlHTTKpi0lupHPIL1WydifH9fNqyL2Qfl+xGixno3A9EOAd44mLteMq+2iRR3Q/I5UAG8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c0e9e9752f3ec0cd7db696572003147945ff14ed07f6bd1ff97017cc2deb2b","last_reissued_at":"2026-07-05T09:02:39.388246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:39.388246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small noise analysis for Tikhonov and RKHS regularizations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fei Lu, Quanjun Lang","submitted_at":"2023-05-18T15:50:33Z","abstract_excerpt":"Regularization plays a pivotal role in ill-posed machine learning and inverse problems. However, the fundamental comparative analysis of various regularization norms remains open. We establish a small noise analysis framework to assess the effects of norms in Tikhonov and RKHS regularizations, in the context of ill-posed linear inverse problems with Gaussian noise. This framework studies the convergence rates of regularized estimators in the small noise limit and reveals the potential instability of the conventional L2-regularizer. We solve such instability by proposing an innovative class of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11055","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/2305.11055/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":"2305.11055","created_at":"2026-07-05T09:02:39.388306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11055v2","created_at":"2026-07-05T09:02:39.388306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11055","created_at":"2026-07-05T09:02:39.388306+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDAOT2LVF47M","created_at":"2026-07-05T09:02:39.388306+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDAOT2LVF47MBTL5","created_at":"2026-07-05T09:02:39.388306+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDAOT2LV","created_at":"2026-07-05T09:02:39.388306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17672","citing_title":"When Rough Data Helps: A Phase Transition in Convergence Rates for Kernel Recovery in Integral Operators","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR","json":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR.json","graph_json":"https://pith.science/api/pith-number/IDAOT2LVF47MBTL5W2LFOIADCR/graph.json","events_json":"https://pith.science/api/pith-number/IDAOT2LVF47MBTL5W2LFOIADCR/events.json","paper":"https://pith.science/paper/IDAOT2LV"},"agent_actions":{"view_html":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR","download_json":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR.json","view_paper":"https://pith.science/paper/IDAOT2LV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11055&json=true","fetch_graph":"https://pith.science/api/pith-number/IDAOT2LVF47MBTL5W2LFOIADCR/graph.json","fetch_events":"https://pith.science/api/pith-number/IDAOT2LVF47MBTL5W2LFOIADCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR/action/storage_attestation","attest_author":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR/action/author_attestation","sign_citation":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR/action/citation_signature","submit_replication":"https://pith.science/pith/IDAOT2LVF47MBTL5W2LFOIADCR/action/replication_record"}},"created_at":"2026-07-05T09:02:39.388306+00:00","updated_at":"2026-07-05T09:02:39.388306+00:00"}