{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QASFNBHRP4RLJT4H3HJ5VKNC6L","short_pith_number":"pith:QASFNBHR","schema_version":"1.0","canonical_sha256":"80245684f17f22b4cf87d9d3daa9a2f2c040e06d07243c1b37df949e0f9c8e41","source":{"kind":"arxiv","id":"1806.01845","version":2},"attestation_state":"computed","paper":{"title":"Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov","submitted_at":"2018-06-06T14:16:36Z","abstract_excerpt":"Several recently proposed architectures of neural networks such as ResNeXt, Inception, Xception, SqueezeNet and Wide ResNet are based on the designing idea of having multiple branches and have demonstrated improved performance in many applications. We show that one cause for such success is due to the fact that the multi-branch architecture is less non-convex in terms of duality gap. The duality gap measures the degree of intrinsic non-convexity of an optimization problem: smaller gap in relative value implies lower degree of intrinsic non-convexity. The challenge is to quantitatively measure "},"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":"1806.01845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:16:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0cf6d512f2b27c54cfb3da50851f3f8682a07c0f71bb853c5fc40715c3b6dc7b","abstract_canon_sha256":"f83534e0cb5cd46c476bb240c2ffa11ce7dd3b9e343693d09c7eb76126397c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:24.100515Z","signature_b64":"QdfcmxojzCL5lrs+843Y4InGmB6Y9UiKo2B5JSZodq9L37WAROQHx2XHqUX17/7cU2/7uJLnpp/fpFTrKx78Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80245684f17f22b4cf87d9d3daa9a2f2c040e06d07243c1b37df949e0f9c8e41","last_reissued_at":"2026-05-18T00:07:24.100007Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:24.100007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov","submitted_at":"2018-06-06T14:16:36Z","abstract_excerpt":"Several recently proposed architectures of neural networks such as ResNeXt, Inception, Xception, SqueezeNet and Wide ResNet are based on the designing idea of having multiple branches and have demonstrated improved performance in many applications. We show that one cause for such success is due to the fact that the multi-branch architecture is less non-convex in terms of duality gap. The duality gap measures the degree of intrinsic non-convexity of an optimization problem: smaller gap in relative value implies lower degree of intrinsic non-convexity. The challenge is to quantitatively measure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01845","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":"1806.01845","created_at":"2026-05-18T00:07:24.100086+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01845v2","created_at":"2026-05-18T00:07:24.100086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01845","created_at":"2026-05-18T00:07:24.100086+00:00"},{"alias_kind":"pith_short_12","alias_value":"QASFNBHRP4RL","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QASFNBHRP4RLJT4H","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QASFNBHR","created_at":"2026-05-18T12:32:46.962924+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/QASFNBHRP4RLJT4H3HJ5VKNC6L","json":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L.json","graph_json":"https://pith.science/api/pith-number/QASFNBHRP4RLJT4H3HJ5VKNC6L/graph.json","events_json":"https://pith.science/api/pith-number/QASFNBHRP4RLJT4H3HJ5VKNC6L/events.json","paper":"https://pith.science/paper/QASFNBHR"},"agent_actions":{"view_html":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L","download_json":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L.json","view_paper":"https://pith.science/paper/QASFNBHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01845&json=true","fetch_graph":"https://pith.science/api/pith-number/QASFNBHRP4RLJT4H3HJ5VKNC6L/graph.json","fetch_events":"https://pith.science/api/pith-number/QASFNBHRP4RLJT4H3HJ5VKNC6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L/action/storage_attestation","attest_author":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L/action/author_attestation","sign_citation":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L/action/citation_signature","submit_replication":"https://pith.science/pith/QASFNBHRP4RLJT4H3HJ5VKNC6L/action/replication_record"}},"created_at":"2026-05-18T00:07:24.100086+00:00","updated_at":"2026-05-18T00:07:24.100086+00:00"}