{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:S2Z7G7EYMRBY622XEOFI7K6ZDN","short_pith_number":"pith:S2Z7G7EY","schema_version":"1.0","canonical_sha256":"96b3f37c9864438f6b57238a8fabd91b4bf722ccc7ab1f5d05d8e1d9831f6879","source":{"kind":"arxiv","id":"1701.05369","version":3},"attestation_state":"computed","paper":{"title":"Variational Dropout Sparsifies Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov","submitted_at":"2017-01-19T10:44:55Z","abstract_excerpt":"We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout. We extend Variational Dropout to the case when dropout rates are unbounded, propose a way to reduce the variance of the gradient estimator and report first experimental results with individual dropout rates per weight. Interestingly, it leads to extremely sparse solutions both in fully-connected and convolutional layers. This effect is similar to automatic relevance determination effect in empirical Bayes but has a number of advantages. We reduce the number of para"},"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":"1701.05369","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-01-19T10:44:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41a7eb497d391b60cbf4350b6f9d9c19205446e53932b431a64efafdf67ef601","abstract_canon_sha256":"5c95c91c41c8070d282a8036a7cfe00f2c4c8e084ad3feeac3b7b7a0826423c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:29.919734Z","signature_b64":"qFfYUYsicaBTET18ViJE974eXI1xxfW5hHDN9bcgbmFZghr3yTP8sBEUwYhiJG3sueaq3y7xuTfhDm9pgFymCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96b3f37c9864438f6b57238a8fabd91b4bf722ccc7ab1f5d05d8e1d9831f6879","last_reissued_at":"2026-05-18T00:42:29.919217Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:29.919217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Dropout Sparsifies Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov","submitted_at":"2017-01-19T10:44:55Z","abstract_excerpt":"We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout. We extend Variational Dropout to the case when dropout rates are unbounded, propose a way to reduce the variance of the gradient estimator and report first experimental results with individual dropout rates per weight. Interestingly, it leads to extremely sparse solutions both in fully-connected and convolutional layers. This effect is similar to automatic relevance determination effect in empirical Bayes but has a number of advantages. We reduce the number of para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05369","kind":"arxiv","version":3},"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":"1701.05369","created_at":"2026-05-18T00:42:29.919299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.05369v3","created_at":"2026-05-18T00:42:29.919299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05369","created_at":"2026-05-18T00:42:29.919299+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2Z7G7EYMRBY","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2Z7G7EYMRBY622X","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2Z7G7EY","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN","json":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN.json","graph_json":"https://pith.science/api/pith-number/S2Z7G7EYMRBY622XEOFI7K6ZDN/graph.json","events_json":"https://pith.science/api/pith-number/S2Z7G7EYMRBY622XEOFI7K6ZDN/events.json","paper":"https://pith.science/paper/S2Z7G7EY"},"agent_actions":{"view_html":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN","download_json":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN.json","view_paper":"https://pith.science/paper/S2Z7G7EY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.05369&json=true","fetch_graph":"https://pith.science/api/pith-number/S2Z7G7EYMRBY622XEOFI7K6ZDN/graph.json","fetch_events":"https://pith.science/api/pith-number/S2Z7G7EYMRBY622XEOFI7K6ZDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN/action/storage_attestation","attest_author":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN/action/author_attestation","sign_citation":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN/action/citation_signature","submit_replication":"https://pith.science/pith/S2Z7G7EYMRBY622XEOFI7K6ZDN/action/replication_record"}},"created_at":"2026-05-18T00:42:29.919299+00:00","updated_at":"2026-05-18T00:42:29.919299+00:00"}