{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ORU2COZJOLXOCTOFVDXCUTXA5Q","short_pith_number":"pith:ORU2COZJ","schema_version":"1.0","canonical_sha256":"7469a13b2972eee14dc5a8ee2a4ee0ec0e07000b2f9efb787f0ae070d9cf968e","source":{"kind":"arxiv","id":"1810.04133","version":2},"attestation_state":"computed","paper":{"title":"Learning One-hidden-layer Neural Networks under General Input Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Vardhan Makkuva, Pramod Viswanath, Sewoong Oh, Weihao Gao","submitted_at":"2018-10-09T16:58:33Z","abstract_excerpt":"Significant advances have been made recently on training neural networks, where the main challenge is in solving an optimization problem with abundant critical points. However, existing approaches to address this issue crucially rely on a restrictive assumption: the training data is drawn from a Gaussian distribution. In this paper, we provide a novel unified framework to design loss functions with desirable landscape properties for a wide range of general input distributions. On these loss functions, remarkably, stochastic gradient descent theoretically recovers the true parameters with globa"},"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":"1810.04133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T16:58:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a7b05292bbaf6f48d71ec4c7a25e4e5491e80c3cd6476c0ad7eb089b7afeb4c2","abstract_canon_sha256":"09b78ae447ab5f24c1a6fd84fcf367b0bd335609f8475f8f9119efb8a3f4bbd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:33.765912Z","signature_b64":"TPogtv+sNXxJo9C+S3SomLA4rdqBICJoUZ5FSMKDO2CqjLIimK0itjw4HaSMNAKF1+Js/s6DsCL4vaOQLTmqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7469a13b2972eee14dc5a8ee2a4ee0ec0e07000b2f9efb787f0ae070d9cf968e","last_reissued_at":"2026-05-17T23:52:33.765488Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:33.765488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning One-hidden-layer Neural Networks under General Input Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Vardhan Makkuva, Pramod Viswanath, Sewoong Oh, Weihao Gao","submitted_at":"2018-10-09T16:58:33Z","abstract_excerpt":"Significant advances have been made recently on training neural networks, where the main challenge is in solving an optimization problem with abundant critical points. However, existing approaches to address this issue crucially rely on a restrictive assumption: the training data is drawn from a Gaussian distribution. In this paper, we provide a novel unified framework to design loss functions with desirable landscape properties for a wide range of general input distributions. On these loss functions, remarkably, stochastic gradient descent theoretically recovers the true parameters with globa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04133","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":"1810.04133","created_at":"2026-05-17T23:52:33.765556+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04133v2","created_at":"2026-05-17T23:52:33.765556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04133","created_at":"2026-05-17T23:52:33.765556+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORU2COZJOLXO","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORU2COZJOLXOCTOF","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORU2COZJ","created_at":"2026-05-18T12:32:43.782077+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/ORU2COZJOLXOCTOFVDXCUTXA5Q","json":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q.json","graph_json":"https://pith.science/api/pith-number/ORU2COZJOLXOCTOFVDXCUTXA5Q/graph.json","events_json":"https://pith.science/api/pith-number/ORU2COZJOLXOCTOFVDXCUTXA5Q/events.json","paper":"https://pith.science/paper/ORU2COZJ"},"agent_actions":{"view_html":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q","download_json":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q.json","view_paper":"https://pith.science/paper/ORU2COZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04133&json=true","fetch_graph":"https://pith.science/api/pith-number/ORU2COZJOLXOCTOFVDXCUTXA5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ORU2COZJOLXOCTOFVDXCUTXA5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q/action/storage_attestation","attest_author":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q/action/author_attestation","sign_citation":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q/action/citation_signature","submit_replication":"https://pith.science/pith/ORU2COZJOLXOCTOFVDXCUTXA5Q/action/replication_record"}},"created_at":"2026-05-17T23:52:33.765556+00:00","updated_at":"2026-05-17T23:52:33.765556+00:00"}