{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZVQLEORZ7VHDXCTGKEKQBYLY27","short_pith_number":"pith:ZVQLEORZ","schema_version":"1.0","canonical_sha256":"cd60b23a39fd4e3b8a66511500e178d7e938ccd719faa53f869d92c4dfd62116","source":{"kind":"arxiv","id":"1506.03208","version":1},"attestation_state":"computed","paper":{"title":"A Scale Mixture Perspective of Multiplicative Noise in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Anima Anandkumar, Eric Nalisnick, Padhraic Smyth","submitted_at":"2015-06-10T08:33:05Z","abstract_excerpt":"Corrupting the input and hidden layers of deep neural networks (DNNs) with multiplicative noise, often drawn from the Bernoulli distribution (or 'dropout'), provides regularization that has significantly contributed to deep learning's success. However, understanding how multiplicative corruptions prevent overfitting has been difficult due to the complexity of a DNN's functional form. In this paper, we show that when a Gaussian prior is placed on a DNN's weights, applying multiplicative noise induces a Gaussian scale mixture, which can be reparameterized to circumvent the problematic likelihood"},"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":"1506.03208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-10T08:33:05Z","cross_cats_sorted":[],"title_canon_sha256":"719f78d9629786dfe9a4664c2c84c88d9e172d10e298f1505281155093cafc6a","abstract_canon_sha256":"25f9efcd281613114b67115a85ebf9c1b15953ae4dd89aa214843afb2df4b3a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:31.254444Z","signature_b64":"QLj/WHqOKm0w4qfgtMnsYf0KQuQ+LaxMnF+XY69Uhg7acsp85F0vxOwb2WIU9RkX5+rIT9jMxJEZ//27TS7bDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd60b23a39fd4e3b8a66511500e178d7e938ccd719faa53f869d92c4dfd62116","last_reissued_at":"2026-05-18T01:55:31.253852Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:31.253852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Scale Mixture Perspective of Multiplicative Noise in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Anima Anandkumar, Eric Nalisnick, Padhraic Smyth","submitted_at":"2015-06-10T08:33:05Z","abstract_excerpt":"Corrupting the input and hidden layers of deep neural networks (DNNs) with multiplicative noise, often drawn from the Bernoulli distribution (or 'dropout'), provides regularization that has significantly contributed to deep learning's success. However, understanding how multiplicative corruptions prevent overfitting has been difficult due to the complexity of a DNN's functional form. In this paper, we show that when a Gaussian prior is placed on a DNN's weights, applying multiplicative noise induces a Gaussian scale mixture, which can be reparameterized to circumvent the problematic likelihood"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03208","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":"1506.03208","created_at":"2026-05-18T01:55:31.253955+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03208v1","created_at":"2026-05-18T01:55:31.253955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03208","created_at":"2026-05-18T01:55:31.253955+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVQLEORZ7VHD","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVQLEORZ7VHDXCTG","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVQLEORZ","created_at":"2026-05-18T12:29:52.810259+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/ZVQLEORZ7VHDXCTGKEKQBYLY27","json":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27.json","graph_json":"https://pith.science/api/pith-number/ZVQLEORZ7VHDXCTGKEKQBYLY27/graph.json","events_json":"https://pith.science/api/pith-number/ZVQLEORZ7VHDXCTGKEKQBYLY27/events.json","paper":"https://pith.science/paper/ZVQLEORZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27","download_json":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27.json","view_paper":"https://pith.science/paper/ZVQLEORZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03208&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVQLEORZ7VHDXCTGKEKQBYLY27/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVQLEORZ7VHDXCTGKEKQBYLY27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27/action/storage_attestation","attest_author":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27/action/author_attestation","sign_citation":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27/action/citation_signature","submit_replication":"https://pith.science/pith/ZVQLEORZ7VHDXCTGKEKQBYLY27/action/replication_record"}},"created_at":"2026-05-18T01:55:31.253955+00:00","updated_at":"2026-05-18T01:55:31.253955+00:00"}