{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:WHMR7YVQYGJ4JD337N3DCBQLER","short_pith_number":"pith:WHMR7YVQ","schema_version":"1.0","canonical_sha256":"b1d91fe2b0c193c48f7bfb7631060b246825b5425d58fcef9570d199717c1d91","source":{"kind":"arxiv","id":"1509.06061","version":1},"attestation_state":"computed","paper":{"title":"A Statistical Theory of Deep Learning via Proximal Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Brandon T. Willard, Massoud Heidari, Nicholas G. Polson","submitted_at":"2015-09-20T21:39:47Z","abstract_excerpt":"In this paper we develop a statistical theory and an implementation of deep learning models. We show that an elegant variable splitting scheme for the alternating direction method of multipliers optimises a deep learning objective. We allow for non-smooth non-convex regularisation penalties to induce sparsity in parameter weights. We provide a link between traditional shallow layer statistical models such as principal component and sliced inverse regression and deep layer models. We also define the degrees of freedom of a deep learning predictor and a predictive MSE criteria to perform model s"},"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":"1509.06061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-09-20T21:39:47Z","cross_cats_sorted":[],"title_canon_sha256":"448d120eab20030867ac795b23453fb14addbe28ed594bb8c9db0806bf909e61","abstract_canon_sha256":"f2660126087dee8a2e8ac85967091d62d15ddf61002a6125a28c3e1296fd9169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:35.972144Z","signature_b64":"yNhkwQ8i0qUiGCvmzzBEiwApntlARo6yjuCc8PW/cQi8N4KpHwA2hj9EY8Wv9RJJPeh9znDLoYjeq38kq1qWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1d91fe2b0c193c48f7bfb7631060b246825b5425d58fcef9570d199717c1d91","last_reissued_at":"2026-05-18T01:32:35.971739Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:35.971739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Statistical Theory of Deep Learning via Proximal Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Brandon T. Willard, Massoud Heidari, Nicholas G. Polson","submitted_at":"2015-09-20T21:39:47Z","abstract_excerpt":"In this paper we develop a statistical theory and an implementation of deep learning models. We show that an elegant variable splitting scheme for the alternating direction method of multipliers optimises a deep learning objective. We allow for non-smooth non-convex regularisation penalties to induce sparsity in parameter weights. We provide a link between traditional shallow layer statistical models such as principal component and sliced inverse regression and deep layer models. We also define the degrees of freedom of a deep learning predictor and a predictive MSE criteria to perform model s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06061","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":"1509.06061","created_at":"2026-05-18T01:32:35.971800+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.06061v1","created_at":"2026-05-18T01:32:35.971800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06061","created_at":"2026-05-18T01:32:35.971800+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHMR7YVQYGJ4","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHMR7YVQYGJ4JD33","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHMR7YVQ","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18857","citing_title":"Task Switching Without Forgetting via Proximal Decoupling","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER","json":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER.json","graph_json":"https://pith.science/api/pith-number/WHMR7YVQYGJ4JD337N3DCBQLER/graph.json","events_json":"https://pith.science/api/pith-number/WHMR7YVQYGJ4JD337N3DCBQLER/events.json","paper":"https://pith.science/paper/WHMR7YVQ"},"agent_actions":{"view_html":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER","download_json":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER.json","view_paper":"https://pith.science/paper/WHMR7YVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.06061&json=true","fetch_graph":"https://pith.science/api/pith-number/WHMR7YVQYGJ4JD337N3DCBQLER/graph.json","fetch_events":"https://pith.science/api/pith-number/WHMR7YVQYGJ4JD337N3DCBQLER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER/action/storage_attestation","attest_author":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER/action/author_attestation","sign_citation":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER/action/citation_signature","submit_replication":"https://pith.science/pith/WHMR7YVQYGJ4JD337N3DCBQLER/action/replication_record"}},"created_at":"2026-05-18T01:32:35.971800+00:00","updated_at":"2026-05-18T01:32:35.971800+00:00"}