{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:E5MBQXPQJCIRC24OZSS7AUQCGD","short_pith_number":"pith:E5MBQXPQ","schema_version":"1.0","canonical_sha256":"2758185df04891116b8ecca5f0520230c5bcd03f9ea25e11219fe61f6813a7e9","source":{"kind":"arxiv","id":"1810.07378","version":2},"attestation_state":"computed","paper":{"title":"Progressive Weight Pruning of Deep Neural Networks using ADMM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fuxun Yu, Jian Tang, Jiayu Li, Kaidi Xu, Kaiqi Zhang, Makan Fardad, Shaokai Ye, Sijia Liu, Tianyun Zhang, Xiang Chen, Xue Lin, Yanzhi Wang, Yunfei Yang","submitted_at":"2018-10-17T03:51:38Z","abstract_excerpt":"Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approaches. This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints. Motivated by dynamic programming, the proposed"},"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":"1810.07378","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-17T03:51:38Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"346b06512c26956eb66375a773f4bc714fcd8ec3fe989c010b6a6ddb816df680","abstract_canon_sha256":"30617ad20921df4e49a7b09d91e8fb3d0260b91343bb61d572860b5156ad97aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:37.525044Z","signature_b64":"MuGDEdU6PUidjljBtsXKMJkd02g2t3nyS4d29ve7iAy+DrkPe/SWqdXx/OGAf2QWp7FbZEgM7bKiE23afQggAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2758185df04891116b8ecca5f0520230c5bcd03f9ea25e11219fe61f6813a7e9","last_reissued_at":"2026-05-18T00:01:37.524427Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:37.524427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Weight Pruning of Deep Neural Networks using ADMM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fuxun Yu, Jian Tang, Jiayu Li, Kaidi Xu, Kaiqi Zhang, Makan Fardad, Shaokai Ye, Sijia Liu, Tianyun Zhang, Xiang Chen, Xue Lin, Yanzhi Wang, Yunfei Yang","submitted_at":"2018-10-17T03:51:38Z","abstract_excerpt":"Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approaches. This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints. Motivated by dynamic programming, the proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07378","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":"1810.07378","created_at":"2026-05-18T00:01:37.524515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07378v2","created_at":"2026-05-18T00:01:37.524515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07378","created_at":"2026-05-18T00:01:37.524515+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5MBQXPQJCIR","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5MBQXPQJCIRC24O","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5MBQXPQ","created_at":"2026-05-18T12:32:19.392346+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/E5MBQXPQJCIRC24OZSS7AUQCGD","json":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD.json","graph_json":"https://pith.science/api/pith-number/E5MBQXPQJCIRC24OZSS7AUQCGD/graph.json","events_json":"https://pith.science/api/pith-number/E5MBQXPQJCIRC24OZSS7AUQCGD/events.json","paper":"https://pith.science/paper/E5MBQXPQ"},"agent_actions":{"view_html":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD","download_json":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD.json","view_paper":"https://pith.science/paper/E5MBQXPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07378&json=true","fetch_graph":"https://pith.science/api/pith-number/E5MBQXPQJCIRC24OZSS7AUQCGD/graph.json","fetch_events":"https://pith.science/api/pith-number/E5MBQXPQJCIRC24OZSS7AUQCGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD/action/storage_attestation","attest_author":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD/action/author_attestation","sign_citation":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD/action/citation_signature","submit_replication":"https://pith.science/pith/E5MBQXPQJCIRC24OZSS7AUQCGD/action/replication_record"}},"created_at":"2026-05-18T00:01:37.524515+00:00","updated_at":"2026-05-18T00:01:37.524515+00:00"}