{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NSHN56BNA2VORLAWP4BXCXM7CN","short_pith_number":"pith:NSHN56BN","schema_version":"1.0","canonical_sha256":"6c8edef82d06aae8ac167f03715d9f135c6d1c59f78f0bb6b983ded17b8838b2","source":{"kind":"arxiv","id":"2304.06959","version":1},"attestation_state":"computed","paper":{"title":"Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunyan Xiong, Di Guo, Jian Cao, Mengli Lu, Xiaobo Qu, Xiaotong Yu, Zhong Chen","submitted_at":"2023-04-14T07:04:07Z","abstract_excerpt":"Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature of nonlinearity and nonconvexity, the training process heavily depends on an appropriate initialization of network parameters, resulting in the difficulty of obtaining a globally optimal solution. To address this issue, a convex dual network is designed here. We theoretically analyze the network convexity and numerically confirm that the strong duality holds. This conclusion is further verified in the linear fitting"},"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":"2304.06959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T07:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"ee92a2bbed9b08851ae78f9ec70566075caeff3805b918cc3fc3874d8f33aae5","abstract_canon_sha256":"0a1467a991131786b9cc63c6897a674a24a9d59f5a4f307381e9a146c6f7f23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:03.677063Z","signature_b64":"CsVnPOQAEWPZlsyCR+vBMD203n30yuQNs5pQHB2nBdk7Guip0pR3w57fSvnteBjEm1TOB2mxJ6WDOuP2iXNfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c8edef82d06aae8ac167f03715d9f135c6d1c59f78f0bb6b983ded17b8838b2","last_reissued_at":"2026-07-05T06:01:03.676697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:03.676697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunyan Xiong, Di Guo, Jian Cao, Mengli Lu, Xiaobo Qu, Xiaotong Yu, Zhong Chen","submitted_at":"2023-04-14T07:04:07Z","abstract_excerpt":"Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature of nonlinearity and nonconvexity, the training process heavily depends on an appropriate initialization of network parameters, resulting in the difficulty of obtaining a globally optimal solution. To address this issue, a convex dual network is designed here. We theoretically analyze the network convexity and numerically confirm that the strong duality holds. This conclusion is further verified in the linear fitting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06959","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.06959/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2304.06959","created_at":"2026-07-05T06:01:03.676752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06959v1","created_at":"2026-07-05T06:01:03.676752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06959","created_at":"2026-07-05T06:01:03.676752+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSHN56BNA2VO","created_at":"2026-07-05T06:01:03.676752+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSHN56BNA2VORLAW","created_at":"2026-07-05T06:01:03.676752+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSHN56BN","created_at":"2026-07-05T06:01:03.676752+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/NSHN56BNA2VORLAWP4BXCXM7CN","json":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN.json","graph_json":"https://pith.science/api/pith-number/NSHN56BNA2VORLAWP4BXCXM7CN/graph.json","events_json":"https://pith.science/api/pith-number/NSHN56BNA2VORLAWP4BXCXM7CN/events.json","paper":"https://pith.science/paper/NSHN56BN"},"agent_actions":{"view_html":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN","download_json":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN.json","view_paper":"https://pith.science/paper/NSHN56BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06959&json=true","fetch_graph":"https://pith.science/api/pith-number/NSHN56BNA2VORLAWP4BXCXM7CN/graph.json","fetch_events":"https://pith.science/api/pith-number/NSHN56BNA2VORLAWP4BXCXM7CN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN/action/storage_attestation","attest_author":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN/action/author_attestation","sign_citation":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN/action/citation_signature","submit_replication":"https://pith.science/pith/NSHN56BNA2VORLAWP4BXCXM7CN/action/replication_record"}},"created_at":"2026-07-05T06:01:03.676752+00:00","updated_at":"2026-07-05T06:01:03.676752+00:00"}