{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2MY2NUXRJOX23EIYWL5RFHZ5A2","short_pith_number":"pith:2MY2NUXR","schema_version":"1.0","canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","source":{"kind":"arxiv","id":"1711.06528","version":2},"attestation_state":"computed","paper":{"title":"Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhen Wei, Houfeng Wang, Jingjing Xu, Shuming Ma, Wei Li, Xuancheng Ren, Xu Sun, Yi Zhang","submitted_at":"2017-11-17T13:36:51Z","abstract_excerpt":"We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude) are kept. As a result, only k rows or columns (depending on the layout) of the weight matrix are modified, leading to a linear reduction in the computational cost. Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldo"},"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":"1711.06528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a5d999571c5d49ddbd43b385a1bea0b71fb0ec942d25a84caf351c0fa2fff0c4","abstract_canon_sha256":"a68d691bf6d7fd6617f4b70001cc20bc33889551059cbc2a116df5e9405ca5b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:34.316480Z","signature_b64":"fgQTPetQvbG5gVuCFCKlYkBONJzRWLDMRQcSHweGS7MCHAn8M18C5QG/7ZXtL52xoVoWFfc1nHO1GzSMDsZyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","last_reissued_at":"2026-05-17T23:51:34.315821Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:34.315821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhen Wei, Houfeng Wang, Jingjing Xu, Shuming Ma, Wei Li, Xuancheng Ren, Xu Sun, Yi Zhang","submitted_at":"2017-11-17T13:36:51Z","abstract_excerpt":"We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude) are kept. As a result, only k rows or columns (depending on the layout) of the weight matrix are modified, leading to a linear reduction in the computational cost. Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06528","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":"1711.06528","created_at":"2026-05-17T23:51:34.315934+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.06528v2","created_at":"2026-05-17T23:51:34.315934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06528","created_at":"2026-05-17T23:51:34.315934+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MY2NUXRJOX2","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MY2NUXRJOX23EIY","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MY2NUXR","created_at":"2026-05-18T12:30:55.937587+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/2MY2NUXRJOX23EIYWL5RFHZ5A2","json":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2.json","graph_json":"https://pith.science/api/pith-number/2MY2NUXRJOX23EIYWL5RFHZ5A2/graph.json","events_json":"https://pith.science/api/pith-number/2MY2NUXRJOX23EIYWL5RFHZ5A2/events.json","paper":"https://pith.science/paper/2MY2NUXR"},"agent_actions":{"view_html":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2","download_json":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2.json","view_paper":"https://pith.science/paper/2MY2NUXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.06528&json=true","fetch_graph":"https://pith.science/api/pith-number/2MY2NUXRJOX23EIYWL5RFHZ5A2/graph.json","fetch_events":"https://pith.science/api/pith-number/2MY2NUXRJOX23EIYWL5RFHZ5A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/action/storage_attestation","attest_author":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/action/author_attestation","sign_citation":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/action/citation_signature","submit_replication":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/action/replication_record"}},"created_at":"2026-05-17T23:51:34.315934+00:00","updated_at":"2026-05-17T23:51:34.315934+00:00"}