{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WXIYZODAAE2JF3UZ7GOHQNROFP","short_pith_number":"pith:WXIYZODA","schema_version":"1.0","canonical_sha256":"b5d18cb860013492ee99f99c78362e2bf7b84dab46202bec912327b148153699","source":{"kind":"arxiv","id":"1805.10767","version":1},"attestation_state":"computed","paper":{"title":"Understanding Generalization and Optimization Performance of Deep CNNs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jiashi Feng, Pan Zhou","submitted_at":"2018-05-28T04:39:24Z","abstract_excerpt":"This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consisting of $l$ convolutional layers and one fully connected layer, we prove that its generalization error is bounded by $\\mathcal{O}(\\sqrt{\\dt\\widetilde{\\varrho}/n})$ where $\\theta$ denotes freedom degree of the network parameters and $\\widetilde{\\varrho}=\\mathcal{O}(\\log(\\prod_{i=1}^{l}\\rwi{i} (\\ki{i}-\\s"},"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":"1805.10767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T04:39:24Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"6c7fcfdf19ea9bf756fe27db5e9a37f2652f088b2177440ae48340e7faab3a36","abstract_canon_sha256":"7a6c5ec45e60ee0b899779b47af4fe8a37cc157baf2397c35ffc66cbf3b44d75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:51.489678Z","signature_b64":"NIDHS2l0kM4giAesra7IkuB5cqpPsG5Gszsy5Uz5pVpcEVNsl/yIPXZi9W7WyYFMzrDncFM+ka62HinsZuvZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d18cb860013492ee99f99c78362e2bf7b84dab46202bec912327b148153699","last_reissued_at":"2026-05-18T00:14:51.489006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:51.489006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Generalization and Optimization Performance of Deep CNNs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jiashi Feng, Pan Zhou","submitted_at":"2018-05-28T04:39:24Z","abstract_excerpt":"This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consisting of $l$ convolutional layers and one fully connected layer, we prove that its generalization error is bounded by $\\mathcal{O}(\\sqrt{\\dt\\widetilde{\\varrho}/n})$ where $\\theta$ denotes freedom degree of the network parameters and $\\widetilde{\\varrho}=\\mathcal{O}(\\log(\\prod_{i=1}^{l}\\rwi{i} (\\ki{i}-\\s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10767","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":""},"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":"1805.10767","created_at":"2026-05-18T00:14:51.489119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10767v1","created_at":"2026-05-18T00:14:51.489119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10767","created_at":"2026-05-18T00:14:51.489119+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXIYZODAAE2J","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXIYZODAAE2JF3UZ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXIYZODA","created_at":"2026-05-18T12:33:01.666342+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/WXIYZODAAE2JF3UZ7GOHQNROFP","json":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP.json","graph_json":"https://pith.science/api/pith-number/WXIYZODAAE2JF3UZ7GOHQNROFP/graph.json","events_json":"https://pith.science/api/pith-number/WXIYZODAAE2JF3UZ7GOHQNROFP/events.json","paper":"https://pith.science/paper/WXIYZODA"},"agent_actions":{"view_html":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP","download_json":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP.json","view_paper":"https://pith.science/paper/WXIYZODA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10767&json=true","fetch_graph":"https://pith.science/api/pith-number/WXIYZODAAE2JF3UZ7GOHQNROFP/graph.json","fetch_events":"https://pith.science/api/pith-number/WXIYZODAAE2JF3UZ7GOHQNROFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP/action/storage_attestation","attest_author":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP/action/author_attestation","sign_citation":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP/action/citation_signature","submit_replication":"https://pith.science/pith/WXIYZODAAE2JF3UZ7GOHQNROFP/action/replication_record"}},"created_at":"2026-05-18T00:14:51.489119+00:00","updated_at":"2026-05-18T00:14:51.489119+00:00"}