{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TE33GGZVOZ5NPG7LCJAXU2HSOM","short_pith_number":"pith:TE33GGZV","schema_version":"1.0","canonical_sha256":"9937b31b35767ad79beb12417a68f2731619a16a69214a435386884ec708638b","source":{"kind":"arxiv","id":"1812.00353","version":2},"attestation_state":"computed","paper":{"title":"Accelerate CNN via Recursive Bayesian Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qi Tian, Yanfeng Wang, Ya Zhang, Yuefu Zhou","submitted_at":"2018-12-02T08:13:10Z","abstract_excerpt":"Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise Recursive Bayesian Pruning method (RBP). A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced. Specifically, we model the noise across layers as a Markov chain and target its posterior to refl"},"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":"1812.00353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T08:13:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a78565f3947cf2eecee4ddabdbea99d478e5c4b6fb418dc2c5d0c3f00e4581d","abstract_canon_sha256":"96867680fb59e808751534a44292cccc3913586a77705f841745a55d7cda5d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:06.717572Z","signature_b64":"R69CpuUovMcAy/gyBDsVZUFNNsjUhxqHOIqUfhvjfHa8dUtGXh5j0uLR+VCMVT3WH5A8mfP28y0OHQLoC/tgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9937b31b35767ad79beb12417a68f2731619a16a69214a435386884ec708638b","last_reissued_at":"2026-05-17T23:50:06.717134Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:06.717134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerate CNN via Recursive Bayesian Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qi Tian, Yanfeng Wang, Ya Zhang, Yuefu Zhou","submitted_at":"2018-12-02T08:13:10Z","abstract_excerpt":"Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise Recursive Bayesian Pruning method (RBP). A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced. Specifically, we model the noise across layers as a Markov chain and target its posterior to refl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00353","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":"1812.00353","created_at":"2026-05-17T23:50:06.717194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00353v2","created_at":"2026-05-17T23:50:06.717194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00353","created_at":"2026-05-17T23:50:06.717194+00:00"},{"alias_kind":"pith_short_12","alias_value":"TE33GGZVOZ5N","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TE33GGZVOZ5NPG7L","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TE33GGZV","created_at":"2026-05-18T12:32:53.628368+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/TE33GGZVOZ5NPG7LCJAXU2HSOM","json":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM.json","graph_json":"https://pith.science/api/pith-number/TE33GGZVOZ5NPG7LCJAXU2HSOM/graph.json","events_json":"https://pith.science/api/pith-number/TE33GGZVOZ5NPG7LCJAXU2HSOM/events.json","paper":"https://pith.science/paper/TE33GGZV"},"agent_actions":{"view_html":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM","download_json":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM.json","view_paper":"https://pith.science/paper/TE33GGZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00353&json=true","fetch_graph":"https://pith.science/api/pith-number/TE33GGZVOZ5NPG7LCJAXU2HSOM/graph.json","fetch_events":"https://pith.science/api/pith-number/TE33GGZVOZ5NPG7LCJAXU2HSOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM/action/storage_attestation","attest_author":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM/action/author_attestation","sign_citation":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM/action/citation_signature","submit_replication":"https://pith.science/pith/TE33GGZVOZ5NPG7LCJAXU2HSOM/action/replication_record"}},"created_at":"2026-05-17T23:50:06.717194+00:00","updated_at":"2026-05-17T23:50:06.717194+00:00"}