{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KRWTLTNQ5QRV3RWYSRLUJOU53F","short_pith_number":"pith:KRWTLTNQ","schema_version":"1.0","canonical_sha256":"546d35cdb0ec235dc6d8945744ba9dd9676487c6ebe831f10fbf954e155b23b4","source":{"kind":"arxiv","id":"1806.00572","version":3},"attestation_state":"computed","paper":{"title":"Autoencoders Learn Generative Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chinmay Hegde, Raymond K. W. Wong, Thanh V. Nguyen","submitted_at":"2018-06-02T02:24:16Z","abstract_excerpt":"We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding model, and (iii) the sparsity model with non-negative coefficients. For each of these models, we prove that under suitable choices of hyperparameters, architectures, and initialization, autoencoders learned by gradient descent can successfully recover the parameters of the correspon"},"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":"1806.00572","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-02T02:24:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a56fb79ac522a054869a1932c6e0ff3c2b0c19abae32d66923e2650164e9969a","abstract_canon_sha256":"ef50117ba5df1a761afd469dfb981c0f5b2d6dd45b7dd99dcc1b67dca659eafb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:57.653074Z","signature_b64":"wHVYfYSfknfHOKfrHzvzXjPwUIkmzWHDPEpmGw5xBNnA3HXxqOtwTJFILpkjII4AeVGc8mbeJhQnNLslrq1/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546d35cdb0ec235dc6d8945744ba9dd9676487c6ebe831f10fbf954e155b23b4","last_reissued_at":"2026-05-17T23:53:57.652460Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:57.652460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoencoders Learn Generative Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chinmay Hegde, Raymond K. W. Wong, Thanh V. Nguyen","submitted_at":"2018-06-02T02:24:16Z","abstract_excerpt":"We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding model, and (iii) the sparsity model with non-negative coefficients. For each of these models, we prove that under suitable choices of hyperparameters, architectures, and initialization, autoencoders learned by gradient descent can successfully recover the parameters of the correspon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00572","kind":"arxiv","version":3},"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":"1806.00572","created_at":"2026-05-17T23:53:57.652560+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00572v3","created_at":"2026-05-17T23:53:57.652560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00572","created_at":"2026-05-17T23:53:57.652560+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRWTLTNQ5QRV","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRWTLTNQ5QRV3RWY","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRWTLTNQ","created_at":"2026-05-18T12:32:33.847187+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/KRWTLTNQ5QRV3RWYSRLUJOU53F","json":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F.json","graph_json":"https://pith.science/api/pith-number/KRWTLTNQ5QRV3RWYSRLUJOU53F/graph.json","events_json":"https://pith.science/api/pith-number/KRWTLTNQ5QRV3RWYSRLUJOU53F/events.json","paper":"https://pith.science/paper/KRWTLTNQ"},"agent_actions":{"view_html":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F","download_json":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F.json","view_paper":"https://pith.science/paper/KRWTLTNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00572&json=true","fetch_graph":"https://pith.science/api/pith-number/KRWTLTNQ5QRV3RWYSRLUJOU53F/graph.json","fetch_events":"https://pith.science/api/pith-number/KRWTLTNQ5QRV3RWYSRLUJOU53F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F/action/storage_attestation","attest_author":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F/action/author_attestation","sign_citation":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F/action/citation_signature","submit_replication":"https://pith.science/pith/KRWTLTNQ5QRV3RWYSRLUJOU53F/action/replication_record"}},"created_at":"2026-05-17T23:53:57.652560+00:00","updated_at":"2026-05-17T23:53:57.652560+00:00"}