{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TZI42BCYJ2B4DUW36HOFNA3CCI","short_pith_number":"pith:TZI42BCY","schema_version":"1.0","canonical_sha256":"9e51cd04584e83c1d2dbf1dc56836212004864e484b7b6b016b4dc6b137ec808","source":{"kind":"arxiv","id":"1804.05345","version":6},"attestation_state":"computed","paper":{"title":"Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Igor Gilitschenski, Lucas Liebenwein","submitted_at":"2018-04-15T12:22:23Z","abstract_excerpt":"We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over the neural network parameters, and as a result, retains parameters of high importance while discarding redundant ones. We leverage a novel, empirical notion of sensitivity and extend traditional coreset constructions to the application of compressing parameters. Our theoretical "},"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":"1804.05345","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-15T12:22:23Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"e2bd9cac43cd0373dc2fe0b32ad7a502f2373fd5f5832839185e93e456fdac51","abstract_canon_sha256":"22dede733e4218cce1001b4138293a96ad719fee411f6b04155707134b4d4628"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:53.164534Z","signature_b64":"nsCLjGgYXdA9UB8UHEdjNkCbvY+uLmzwYlQRaWA8CxFPhCOzl/Xxm4M78e53IBe7ycPJ2bQPiCCNRscl3vPSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e51cd04584e83c1d2dbf1dc56836212004864e484b7b6b016b4dc6b137ec808","last_reissued_at":"2026-05-17T23:45:53.163932Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:53.163932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Igor Gilitschenski, Lucas Liebenwein","submitted_at":"2018-04-15T12:22:23Z","abstract_excerpt":"We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over the neural network parameters, and as a result, retains parameters of high importance while discarding redundant ones. We leverage a novel, empirical notion of sensitivity and extend traditional coreset constructions to the application of compressing parameters. Our theoretical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05345","kind":"arxiv","version":6},"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":"1804.05345","created_at":"2026-05-17T23:45:53.164020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05345v6","created_at":"2026-05-17T23:45:53.164020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05345","created_at":"2026-05-17T23:45:53.164020+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZI42BCYJ2B4","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZI42BCYJ2B4DUW3","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZI42BCY","created_at":"2026-05-18T12:32:56.356000+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/TZI42BCYJ2B4DUW36HOFNA3CCI","json":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI.json","graph_json":"https://pith.science/api/pith-number/TZI42BCYJ2B4DUW36HOFNA3CCI/graph.json","events_json":"https://pith.science/api/pith-number/TZI42BCYJ2B4DUW36HOFNA3CCI/events.json","paper":"https://pith.science/paper/TZI42BCY"},"agent_actions":{"view_html":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI","download_json":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI.json","view_paper":"https://pith.science/paper/TZI42BCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05345&json=true","fetch_graph":"https://pith.science/api/pith-number/TZI42BCYJ2B4DUW36HOFNA3CCI/graph.json","fetch_events":"https://pith.science/api/pith-number/TZI42BCYJ2B4DUW36HOFNA3CCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI/action/storage_attestation","attest_author":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI/action/author_attestation","sign_citation":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI/action/citation_signature","submit_replication":"https://pith.science/pith/TZI42BCYJ2B4DUW36HOFNA3CCI/action/replication_record"}},"created_at":"2026-05-17T23:45:53.164020+00:00","updated_at":"2026-05-17T23:45:53.164020+00:00"}