{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:435UTAPEEBP3UFKXR3R2HRUA7V","short_pith_number":"pith:435UTAPE","schema_version":"1.0","canonical_sha256":"e6fb4981e4205fba15578ee3a3c680fd6aefea450b6b4d06a3a50bfa1c2fc3af","source":{"kind":"arxiv","id":"1502.03537","version":1},"attestation_state":"computed","paper":{"title":"Convergence of gradient based pre-training in Denoising autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"cs.LG","authors_text":"Sathya Ravi, Vamsi K Ithapu, Vikas Singh","submitted_at":"2015-02-12T04:31:36Z","abstract_excerpt":"The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network. Various papers have reported extensive empirical analysis focusing on the design and implementation of good pre-training procedures. However, an understanding pertaining to the consistency of parameter estimates, the convergence of learning procedures and the sample size estimates is still unavailable in the literature. In this work, we study pre-training in classical and distributed denoising autoencoders with these goals in mind. We show that the grad"},"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":"1502.03537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T04:31:36Z","cross_cats_sorted":["cs.CV","math.OC"],"title_canon_sha256":"cdb19104499d6454630fcca39ae2dbcc86485dab2cc0b2279f98fc13dc728349","abstract_canon_sha256":"3153f796db9eaa8cf082d1d3245ac02cefac80ddc79dd3e77edf53e7c3cfa4e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:27:17.573625Z","signature_b64":"2woy8K4KHH3up0hZ34HxixlMhk8sNxQa7PSusZe60V9dAJZs6NAm5P2zt/lfLMWmPAQtveINxA6ov50xKIHPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6fb4981e4205fba15578ee3a3c680fd6aefea450b6b4d06a3a50bfa1c2fc3af","last_reissued_at":"2026-05-18T02:27:17.572803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:27:17.572803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of gradient based pre-training in Denoising autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"cs.LG","authors_text":"Sathya Ravi, Vamsi K Ithapu, Vikas Singh","submitted_at":"2015-02-12T04:31:36Z","abstract_excerpt":"The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network. Various papers have reported extensive empirical analysis focusing on the design and implementation of good pre-training procedures. However, an understanding pertaining to the consistency of parameter estimates, the convergence of learning procedures and the sample size estimates is still unavailable in the literature. In this work, we study pre-training in classical and distributed denoising autoencoders with these goals in mind. We show that the grad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03537","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":"1502.03537","created_at":"2026-05-18T02:27:17.572930+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.03537v1","created_at":"2026-05-18T02:27:17.572930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03537","created_at":"2026-05-18T02:27:17.572930+00:00"},{"alias_kind":"pith_short_12","alias_value":"435UTAPEEBP3","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"435UTAPEEBP3UFKX","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"435UTAPE","created_at":"2026-05-18T12:29:02.477457+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/435UTAPEEBP3UFKXR3R2HRUA7V","json":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V.json","graph_json":"https://pith.science/api/pith-number/435UTAPEEBP3UFKXR3R2HRUA7V/graph.json","events_json":"https://pith.science/api/pith-number/435UTAPEEBP3UFKXR3R2HRUA7V/events.json","paper":"https://pith.science/paper/435UTAPE"},"agent_actions":{"view_html":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V","download_json":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V.json","view_paper":"https://pith.science/paper/435UTAPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.03537&json=true","fetch_graph":"https://pith.science/api/pith-number/435UTAPEEBP3UFKXR3R2HRUA7V/graph.json","fetch_events":"https://pith.science/api/pith-number/435UTAPEEBP3UFKXR3R2HRUA7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V/action/storage_attestation","attest_author":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V/action/author_attestation","sign_citation":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V/action/citation_signature","submit_replication":"https://pith.science/pith/435UTAPEEBP3UFKXR3R2HRUA7V/action/replication_record"}},"created_at":"2026-05-18T02:27:17.572930+00:00","updated_at":"2026-05-18T02:27:17.572930+00:00"}