{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HRTGTKPFXI5JE4HPSC5GDZKBDD","short_pith_number":"pith:HRTGTKPF","schema_version":"1.0","canonical_sha256":"3c6669a9e5ba3a9270ef90ba61e54118d4ac6fb0647235cad1141335d89d0da3","source":{"kind":"arxiv","id":"1705.10182","version":1},"attestation_state":"computed","paper":{"title":"Fast learning rate of deep learning via a kernel perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Taiji Suzuki","submitted_at":"2017-05-29T13:47:44Z","abstract_excerpt":"We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of theoretical analyses of deep learning has revealed its high expressive power and universal approximation capability. Although these analyses are highly nonparametric, existing generalization error analyses have been developed mainly in a fixed dimensional parametric model. To compensate this gap, we develop an infinite dimensional model that is based on an integra"},"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":"1705.10182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-05-29T13:47:44Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"fef8862c9a7cb34806532a29d03c821702d3821b0860b3537ce7c3a8c379964c","abstract_canon_sha256":"5b9fac42a167dfe9dca1ff179507e0f52d9da8e5e2ef41366e8aaa99d84f042e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:24.682520Z","signature_b64":"d8VomCbUpP8g9NKFh35MNoczN01D9QkwB2zT5B0ltlgdR5vtRnRTk9XLCFHGo/QAUi87hgTS7WvYOQg42xWpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6669a9e5ba3a9270ef90ba61e54118d4ac6fb0647235cad1141335d89d0da3","last_reissued_at":"2026-05-18T00:43:24.681869Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:24.681869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast learning rate of deep learning via a kernel perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Taiji Suzuki","submitted_at":"2017-05-29T13:47:44Z","abstract_excerpt":"We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of theoretical analyses of deep learning has revealed its high expressive power and universal approximation capability. Although these analyses are highly nonparametric, existing generalization error analyses have been developed mainly in a fixed dimensional parametric model. To compensate this gap, we develop an infinite dimensional model that is based on an integra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10182","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":"1705.10182","created_at":"2026-05-18T00:43:24.681978+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.10182v1","created_at":"2026-05-18T00:43:24.681978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10182","created_at":"2026-05-18T00:43:24.681978+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRTGTKPFXI5J","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRTGTKPFXI5JE4HP","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRTGTKPF","created_at":"2026-05-18T12:31:18.294218+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/HRTGTKPFXI5JE4HPSC5GDZKBDD","json":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD.json","graph_json":"https://pith.science/api/pith-number/HRTGTKPFXI5JE4HPSC5GDZKBDD/graph.json","events_json":"https://pith.science/api/pith-number/HRTGTKPFXI5JE4HPSC5GDZKBDD/events.json","paper":"https://pith.science/paper/HRTGTKPF"},"agent_actions":{"view_html":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD","download_json":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD.json","view_paper":"https://pith.science/paper/HRTGTKPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.10182&json=true","fetch_graph":"https://pith.science/api/pith-number/HRTGTKPFXI5JE4HPSC5GDZKBDD/graph.json","fetch_events":"https://pith.science/api/pith-number/HRTGTKPFXI5JE4HPSC5GDZKBDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD/action/storage_attestation","attest_author":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD/action/author_attestation","sign_citation":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD/action/citation_signature","submit_replication":"https://pith.science/pith/HRTGTKPFXI5JE4HPSC5GDZKBDD/action/replication_record"}},"created_at":"2026-05-18T00:43:24.681978+00:00","updated_at":"2026-05-18T00:43:24.681978+00:00"}