{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BZ522QBK5EDTF7QW56CTV4W3IV","short_pith_number":"pith:BZ522QBK","schema_version":"1.0","canonical_sha256":"0e7bad402ae90732fe16ef853af2db4569480ec56d8a63ef788c014a6253dc26","source":{"kind":"arxiv","id":"1602.02220","version":2},"attestation_state":"computed","paper":{"title":"Improved Dropout for Shallow and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boqing Gong, Tianbao Yang, Zhe Li","submitted_at":"2016-02-06T05:41:57Z","abstract_excerpt":"Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of convergence. In this paper, we propose to use multinomial sampling for dropout, i.e., sampling features or neurons according to a multinomial distribution with different probabilities for different features/neurons. To exhibit the optimal dropout probabilities, we analyze the shallow l"},"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":"1602.02220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-06T05:41:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee771d8401a9a8aff91865507acd91e16e2f42ce907ec95608001ea3b062c98f","abstract_canon_sha256":"85acc156ecb0ea5b2cc0dfac119d3a5cc3f6aab1a03d88e07e7d54ce3d383e84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:58.291120Z","signature_b64":"1O6jGGPelE3QzvLy4x8AvNcSloZMHPEk3JoINkTwqgUlS1TdanFnJr7G5L2g1G3QaQD3NmxY0944uemWceJpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e7bad402ae90732fe16ef853af2db4569480ec56d8a63ef788c014a6253dc26","last_reissued_at":"2026-05-18T00:55:58.290742Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:58.290742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Dropout for Shallow and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boqing Gong, Tianbao Yang, Zhe Li","submitted_at":"2016-02-06T05:41:57Z","abstract_excerpt":"Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of convergence. In this paper, we propose to use multinomial sampling for dropout, i.e., sampling features or neurons according to a multinomial distribution with different probabilities for different features/neurons. To exhibit the optimal dropout probabilities, we analyze the shallow l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02220","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":"1602.02220","created_at":"2026-05-18T00:55:58.290803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02220v2","created_at":"2026-05-18T00:55:58.290803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02220","created_at":"2026-05-18T00:55:58.290803+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZ522QBK5EDT","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZ522QBK5EDTF7QW","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZ522QBK","created_at":"2026-05-18T12:30:09.641336+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/BZ522QBK5EDTF7QW56CTV4W3IV","json":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV.json","graph_json":"https://pith.science/api/pith-number/BZ522QBK5EDTF7QW56CTV4W3IV/graph.json","events_json":"https://pith.science/api/pith-number/BZ522QBK5EDTF7QW56CTV4W3IV/events.json","paper":"https://pith.science/paper/BZ522QBK"},"agent_actions":{"view_html":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV","download_json":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV.json","view_paper":"https://pith.science/paper/BZ522QBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02220&json=true","fetch_graph":"https://pith.science/api/pith-number/BZ522QBK5EDTF7QW56CTV4W3IV/graph.json","fetch_events":"https://pith.science/api/pith-number/BZ522QBK5EDTF7QW56CTV4W3IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV/action/storage_attestation","attest_author":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV/action/author_attestation","sign_citation":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV/action/citation_signature","submit_replication":"https://pith.science/pith/BZ522QBK5EDTF7QW56CTV4W3IV/action/replication_record"}},"created_at":"2026-05-18T00:55:58.290803+00:00","updated_at":"2026-05-18T00:55:58.290803+00:00"}