{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TKQPU5M5HTBAUMRWWLIQIRCI44","short_pith_number":"pith:TKQPU5M5","schema_version":"1.0","canonical_sha256":"9aa0fa759d3cc20a3236b2d1044448e7274baebaefbe53a42b68595a9ddb6530","source":{"kind":"arxiv","id":"1905.11320","version":2},"attestation_state":"computed","paper":{"title":"On approximating dropout noise injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Natalie Schluter","submitted_at":"2019-05-27T16:11:42Z","abstract_excerpt":"This paper examines the assumptions of the derived equivalence between dropout noise injection and $L_2$ regularisation for logistic regression with negative log loss. We show that the approximation method is based on a divergent Taylor expansion, making, subsequent work using this approximation to compare the dropout trained logistic regression model with standard regularisers unfortunately ill-founded to date. Moreover, the approximation approach is shown to be invalid using any robust constraints. We show how this finding extends to general neural network topologies that use a cross-entropy"},"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":"1905.11320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T16:11:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1de51d118af19300878ccb5c88e717e84407991e44c8df286f57dec52105cf07","abstract_canon_sha256":"051db91cd3d00625e3aceed0da7405046b2d13e1810fcbc5560d6feb1ea3bbc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.374239Z","signature_b64":"j59/9whRM16nwW1mDQMBd+tfHIlH5bZKE2SkXifQntj0vx/99g0ebVLXS3d5GbR1+d63VfRYCPX2zoQX9zFMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aa0fa759d3cc20a3236b2d1044448e7274baebaefbe53a42b68595a9ddb6530","last_reissued_at":"2026-05-17T23:44:28.373494Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.373494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On approximating dropout noise injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Natalie Schluter","submitted_at":"2019-05-27T16:11:42Z","abstract_excerpt":"This paper examines the assumptions of the derived equivalence between dropout noise injection and $L_2$ regularisation for logistic regression with negative log loss. We show that the approximation method is based on a divergent Taylor expansion, making, subsequent work using this approximation to compare the dropout trained logistic regression model with standard regularisers unfortunately ill-founded to date. Moreover, the approximation approach is shown to be invalid using any robust constraints. We show how this finding extends to general neural network topologies that use a cross-entropy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11320","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":""},"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":"1905.11320","created_at":"2026-05-17T23:44:28.373602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11320v2","created_at":"2026-05-17T23:44:28.373602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11320","created_at":"2026-05-17T23:44:28.373602+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKQPU5M5HTBA","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKQPU5M5HTBAUMRW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKQPU5M5","created_at":"2026-05-18T12:33:30.264802+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/TKQPU5M5HTBAUMRWWLIQIRCI44","json":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44.json","graph_json":"https://pith.science/api/pith-number/TKQPU5M5HTBAUMRWWLIQIRCI44/graph.json","events_json":"https://pith.science/api/pith-number/TKQPU5M5HTBAUMRWWLIQIRCI44/events.json","paper":"https://pith.science/paper/TKQPU5M5"},"agent_actions":{"view_html":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44","download_json":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44.json","view_paper":"https://pith.science/paper/TKQPU5M5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11320&json=true","fetch_graph":"https://pith.science/api/pith-number/TKQPU5M5HTBAUMRWWLIQIRCI44/graph.json","fetch_events":"https://pith.science/api/pith-number/TKQPU5M5HTBAUMRWWLIQIRCI44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44/action/storage_attestation","attest_author":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44/action/author_attestation","sign_citation":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44/action/citation_signature","submit_replication":"https://pith.science/pith/TKQPU5M5HTBAUMRWWLIQIRCI44/action/replication_record"}},"created_at":"2026-05-17T23:44:28.373602+00:00","updated_at":"2026-05-17T23:44:28.373602+00:00"}