{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3HYT534D4MED65JFT2DA624D7F","short_pith_number":"pith:3HYT534D","schema_version":"1.0","canonical_sha256":"d9f13eef83e3083f75259e860f6b83f9722a6d8d741cf5c6d02a1456aa1e4e06","source":{"kind":"arxiv","id":"1806.07808","version":1},"attestation_state":"computed","paper":{"title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lingxiao Wang, Quanquan Gu, Xiao Zhang, Yaodong Yu","submitted_at":"2018-06-20T15:52:43Z","abstract_excerpt":"We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher network. We analyze the performance of gradient descent for training such kind of neural networks based on empirical risk minimization, and provide algorithm-dependent guarantees. In particular, we prove that tensor initialization followed by gradient descent can converge to the ground-truth parameters at a linear rate up to some statistical error. To the best "},"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":"1806.07808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-20T15:52:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e2e38cea472089207075e2192ffa4ac98ec9796c2e7665f7868e3fbf656029cb","abstract_canon_sha256":"0e5b0cc8081803e70b9f7822f45ffc85db5849ed7e0671bab3bfbdc3cdee248d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:46.572416Z","signature_b64":"oZhtUaD15X5z2s9bBkAF+T+G4eatJs0Y2sf7yEdqRb3oNnXZzszqwSDiXwwCF4L5K9Lp4/gpAeT6EBhpAGCsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f13eef83e3083f75259e860f6b83f9722a6d8d741cf5c6d02a1456aa1e4e06","last_reissued_at":"2026-05-18T00:12:46.571679Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:46.571679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lingxiao Wang, Quanquan Gu, Xiao Zhang, Yaodong Yu","submitted_at":"2018-06-20T15:52:43Z","abstract_excerpt":"We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher network. We analyze the performance of gradient descent for training such kind of neural networks based on empirical risk minimization, and provide algorithm-dependent guarantees. In particular, we prove that tensor initialization followed by gradient descent can converge to the ground-truth parameters at a linear rate up to some statistical error. To the best "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07808","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":"1806.07808","created_at":"2026-05-18T00:12:46.571800+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07808v1","created_at":"2026-05-18T00:12:46.571800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07808","created_at":"2026-05-18T00:12:46.571800+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HYT534D4MED","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HYT534D4MED65JF","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HYT534D","created_at":"2026-05-18T12:32:02.567920+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/3HYT534D4MED65JFT2DA624D7F","json":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F.json","graph_json":"https://pith.science/api/pith-number/3HYT534D4MED65JFT2DA624D7F/graph.json","events_json":"https://pith.science/api/pith-number/3HYT534D4MED65JFT2DA624D7F/events.json","paper":"https://pith.science/paper/3HYT534D"},"agent_actions":{"view_html":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F","download_json":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F.json","view_paper":"https://pith.science/paper/3HYT534D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07808&json=true","fetch_graph":"https://pith.science/api/pith-number/3HYT534D4MED65JFT2DA624D7F/graph.json","fetch_events":"https://pith.science/api/pith-number/3HYT534D4MED65JFT2DA624D7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F/action/storage_attestation","attest_author":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F/action/author_attestation","sign_citation":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F/action/citation_signature","submit_replication":"https://pith.science/pith/3HYT534D4MED65JFT2DA624D7F/action/replication_record"}},"created_at":"2026-05-18T00:12:46.571800+00:00","updated_at":"2026-05-18T00:12:46.571800+00:00"}