{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2H2EFHDZLPFPGXQCCJ4PTSPEBZ","short_pith_number":"pith:2H2EFHDZ","schema_version":"1.0","canonical_sha256":"d1f4429c795bcaf35e021278f9c9e40e54b6158d3c089c1e09e5fe1134fb06e8","source":{"kind":"arxiv","id":"2504.08489","version":1},"attestation_state":"computed","paper":{"title":"Statistically guided deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adam Krzyzak, Michael Kohler","submitted_at":"2025-04-11T12:36:06Z","abstract_excerpt":"We present a theoretically well-founded deep learning algorithm for nonparametric regression. It uses over-parametrized deep neural networks with logistic activation function, which are fitted to the given data via gradient descent. We propose a special topology of these networks, a special random initialization of the weights, and a data-dependent choice of the learning rate and the number of gradient descent steps. We prove a theoretical bound on the expected $L_2$ error of this estimate, and illustrate its finite sample size performance by applying it to simulated data. Our results show tha"},"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":"2504.08489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-04-11T12:36:06Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"582cdd5b310258f87468a91b190dab02ca9cdc8038d3ab84cbe90222ad6f01f2","abstract_canon_sha256":"e19a0e6fd67c124051d48a13a3026511957c825892838bfd15e58185f8594414"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:50.153257Z","signature_b64":"6VGWe6isi/zptBzvmxcJWwgR7oWoQpFqYUT4br2wbESKRI9HrndScq6xTPjWx9StOl/+HqiA5KmR6kuo4Ta4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1f4429c795bcaf35e021278f9c9e40e54b6158d3c089c1e09e5fe1134fb06e8","last_reissued_at":"2026-07-05T10:47:50.152791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:50.152791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistically guided deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adam Krzyzak, Michael Kohler","submitted_at":"2025-04-11T12:36:06Z","abstract_excerpt":"We present a theoretically well-founded deep learning algorithm for nonparametric regression. It uses over-parametrized deep neural networks with logistic activation function, which are fitted to the given data via gradient descent. We propose a special topology of these networks, a special random initialization of the weights, and a data-dependent choice of the learning rate and the number of gradient descent steps. We prove a theoretical bound on the expected $L_2$ error of this estimate, and illustrate its finite sample size performance by applying it to simulated data. Our results show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08489","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.08489/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":"2504.08489","created_at":"2026-07-05T10:47:50.152851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08489v1","created_at":"2026-07-05T10:47:50.152851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08489","created_at":"2026-07-05T10:47:50.152851+00:00"},{"alias_kind":"pith_short_12","alias_value":"2H2EFHDZLPFP","created_at":"2026-07-05T10:47:50.152851+00:00"},{"alias_kind":"pith_short_16","alias_value":"2H2EFHDZLPFPGXQC","created_at":"2026-07-05T10:47:50.152851+00:00"},{"alias_kind":"pith_short_8","alias_value":"2H2EFHDZ","created_at":"2026-07-05T10:47:50.152851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ","json":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ.json","graph_json":"https://pith.science/api/pith-number/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/graph.json","events_json":"https://pith.science/api/pith-number/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/events.json","paper":"https://pith.science/paper/2H2EFHDZ"},"agent_actions":{"view_html":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ","download_json":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ.json","view_paper":"https://pith.science/paper/2H2EFHDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08489&json=true","fetch_graph":"https://pith.science/api/pith-number/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/action/storage_attestation","attest_author":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/action/author_attestation","sign_citation":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/action/citation_signature","submit_replication":"https://pith.science/pith/2H2EFHDZLPFPGXQCCJ4PTSPEBZ/action/replication_record"}},"created_at":"2026-07-05T10:47:50.152851+00:00","updated_at":"2026-07-05T10:47:50.152851+00:00"}