{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EDN2KE2MKPPYTLXMGXB23CKL4O","short_pith_number":"pith:EDN2KE2M","schema_version":"1.0","canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","source":{"kind":"arxiv","id":"1812.03599","version":2},"attestation_state":"computed","paper":{"title":"Fast convergence rates of deep neural networks for classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Ilsang Ohn, Yongdai Kim","submitted_at":"2018-12-10T02:41:06Z","abstract_excerpt":"We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity). is carefully "},"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":"1812.03599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3013639bc997df735ffa14193dc5ef04cbf30d144914c6d9522307ce1a9322b8","abstract_canon_sha256":"df0501203b6c55559f8df16a2502e87f1c9bbc176331ee94429667ffe8d7c4d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:09.233638Z","signature_b64":"q1Tu7GvU6PhNwQdGGd5CvXCH/wSpd47eO6Ntcae2unBQxU1SNlieWI3ZzHxzEzDsYC8LzN22VjzwRHMHEBglAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","last_reissued_at":"2026-05-17T23:43:09.233000Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:09.233000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast convergence rates of deep neural networks for classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Ilsang Ohn, Yongdai Kim","submitted_at":"2018-12-10T02:41:06Z","abstract_excerpt":"We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity). is carefully "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03599","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":"1812.03599","created_at":"2026-05-17T23:43:09.233085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03599v2","created_at":"2026-05-17T23:43:09.233085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03599","created_at":"2026-05-17T23:43:09.233085+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDN2KE2MKPPY","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDN2KE2MKPPYTLXM","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDN2KE2M","created_at":"2026-05-18T12:32:22.470017+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/EDN2KE2MKPPYTLXMGXB23CKL4O","json":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O.json","graph_json":"https://pith.science/api/pith-number/EDN2KE2MKPPYTLXMGXB23CKL4O/graph.json","events_json":"https://pith.science/api/pith-number/EDN2KE2MKPPYTLXMGXB23CKL4O/events.json","paper":"https://pith.science/paper/EDN2KE2M"},"agent_actions":{"view_html":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O","download_json":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O.json","view_paper":"https://pith.science/paper/EDN2KE2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03599&json=true","fetch_graph":"https://pith.science/api/pith-number/EDN2KE2MKPPYTLXMGXB23CKL4O/graph.json","fetch_events":"https://pith.science/api/pith-number/EDN2KE2MKPPYTLXMGXB23CKL4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/action/storage_attestation","attest_author":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/action/author_attestation","sign_citation":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/action/citation_signature","submit_replication":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/action/replication_record"}},"created_at":"2026-05-17T23:43:09.233085+00:00","updated_at":"2026-05-17T23:43:09.233085+00:00"}