{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OKGHWA6E6QB7LYEREGFUQF6R2R","short_pith_number":"pith:OKGHWA6E","schema_version":"1.0","canonical_sha256":"728c7b03c4f403f5e091218b4817d1d44b1e1757d6e97071487faa4de3056fe9","source":{"kind":"arxiv","id":"1805.10896","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Network Sparsification with Dependent Variational Beta-Bernoulli Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eunho Yang, Hae Beom Lee, Jaehong Yoon, Juho Lee, Saehoon Kim, Sung Ju Hwang","submitted_at":"2018-05-28T12:50:02Z","abstract_excerpt":"While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss. To overcome this limitation, we propose adaptive variational dropout whose probabilities are drawn from sparsity-inducing beta Bernoulli prior. It allows each neuron to be evolved either to be generic or specific for c"},"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":"1805.10896","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-28T12:50:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c5234e890882fba4b954337d931c2771fae5df97174dd5597b9d2ccef8417a4","abstract_canon_sha256":"7225fa941bdafb46432a4cb135af500297f111f088da46ff5ea8e8485341632c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:18.330500Z","signature_b64":"xyls+oKnAUb8ITRKjfS8eYapZYHCf34HahwCdavcX2PhFfsRFhyi/syBf+CQ7OyK3sMH2+1GKJFALGSnoroBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728c7b03c4f403f5e091218b4817d1d44b1e1757d6e97071487faa4de3056fe9","last_reissued_at":"2026-05-17T23:52:18.329795Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:18.329795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Network Sparsification with Dependent Variational Beta-Bernoulli Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eunho Yang, Hae Beom Lee, Jaehong Yoon, Juho Lee, Saehoon Kim, Sung Ju Hwang","submitted_at":"2018-05-28T12:50:02Z","abstract_excerpt":"While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss. To overcome this limitation, we propose adaptive variational dropout whose probabilities are drawn from sparsity-inducing beta Bernoulli prior. It allows each neuron to be evolved either to be generic or specific for c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10896","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":"1805.10896","created_at":"2026-05-17T23:52:18.329909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10896v3","created_at":"2026-05-17T23:52:18.329909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10896","created_at":"2026-05-17T23:52:18.329909+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKGHWA6E6QB7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKGHWA6E6QB7LYER","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKGHWA6E","created_at":"2026-05-18T12:32:43.782077+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/OKGHWA6E6QB7LYEREGFUQF6R2R","json":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R.json","graph_json":"https://pith.science/api/pith-number/OKGHWA6E6QB7LYEREGFUQF6R2R/graph.json","events_json":"https://pith.science/api/pith-number/OKGHWA6E6QB7LYEREGFUQF6R2R/events.json","paper":"https://pith.science/paper/OKGHWA6E"},"agent_actions":{"view_html":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R","download_json":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R.json","view_paper":"https://pith.science/paper/OKGHWA6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10896&json=true","fetch_graph":"https://pith.science/api/pith-number/OKGHWA6E6QB7LYEREGFUQF6R2R/graph.json","fetch_events":"https://pith.science/api/pith-number/OKGHWA6E6QB7LYEREGFUQF6R2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R/action/storage_attestation","attest_author":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R/action/author_attestation","sign_citation":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R/action/citation_signature","submit_replication":"https://pith.science/pith/OKGHWA6E6QB7LYEREGFUQF6R2R/action/replication_record"}},"created_at":"2026-05-17T23:52:18.329909+00:00","updated_at":"2026-05-17T23:52:18.329909+00:00"}