{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7WR3KKHVY4QRWUES62EPS34PTW","short_pith_number":"pith:7WR3KKHV","schema_version":"1.0","canonical_sha256":"fda3b528f5c7211b5092f688f96f8f9db538fdffff7781d491c121bc9ca3b874","source":{"kind":"arxiv","id":"1711.08911","version":1},"attestation_state":"computed","paper":{"title":"Computing the quality of the Laplace approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guillaume P. Dehaene","submitted_at":"2017-11-24T10:10:15Z","abstract_excerpt":"Bayesian inference requires approximation methods to become computable, but for most of them it is impossible to quantify how close the approximation is to the true posterior. In this work, we present a theorem upper-bounding the KL divergence between a log-concave target density $f\\left(\\boldsymbol{\\theta}\\right)$ and its Laplace approximation $g\\left(\\boldsymbol{\\theta}\\right)$. The bound we present is computable: on the classical logistic regression model, we find our bound to be almost exact as long as the dimensionality of the parameter space is high.\n  The approach we followed in this wo"},"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":"1711.08911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-24T10:10:15Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"15d05aeb98197b55a27dd06479eabffd7dd861361d57e8cfd7efac57070bcc9a","abstract_canon_sha256":"14be2d7c2f92044f095bfb14e0292e47a17da478a9dc96a77446e71b2050d6c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:41.753563Z","signature_b64":"AbpWAJ6+PrBXsR8lLkuPIrYkbDRTf9dSO9aSK16fPGM4t3FaOF3GYIIYF/QSnZM66w8T9Nt91psGvXV90UbJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda3b528f5c7211b5092f688f96f8f9db538fdffff7781d491c121bc9ca3b874","last_reissued_at":"2026-05-18T00:29:41.752928Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:41.752928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computing the quality of the Laplace approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guillaume P. Dehaene","submitted_at":"2017-11-24T10:10:15Z","abstract_excerpt":"Bayesian inference requires approximation methods to become computable, but for most of them it is impossible to quantify how close the approximation is to the true posterior. In this work, we present a theorem upper-bounding the KL divergence between a log-concave target density $f\\left(\\boldsymbol{\\theta}\\right)$ and its Laplace approximation $g\\left(\\boldsymbol{\\theta}\\right)$. The bound we present is computable: on the classical logistic regression model, we find our bound to be almost exact as long as the dimensionality of the parameter space is high.\n  The approach we followed in this wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08911","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":"1711.08911","created_at":"2026-05-18T00:29:41.753028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08911v1","created_at":"2026-05-18T00:29:41.753028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08911","created_at":"2026-05-18T00:29:41.753028+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WR3KKHVY4QR","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WR3KKHVY4QRWUES","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WR3KKHV","created_at":"2026-05-18T12:31:05.417338+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/7WR3KKHVY4QRWUES62EPS34PTW","json":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW.json","graph_json":"https://pith.science/api/pith-number/7WR3KKHVY4QRWUES62EPS34PTW/graph.json","events_json":"https://pith.science/api/pith-number/7WR3KKHVY4QRWUES62EPS34PTW/events.json","paper":"https://pith.science/paper/7WR3KKHV"},"agent_actions":{"view_html":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW","download_json":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW.json","view_paper":"https://pith.science/paper/7WR3KKHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08911&json=true","fetch_graph":"https://pith.science/api/pith-number/7WR3KKHVY4QRWUES62EPS34PTW/graph.json","fetch_events":"https://pith.science/api/pith-number/7WR3KKHVY4QRWUES62EPS34PTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW/action/storage_attestation","attest_author":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW/action/author_attestation","sign_citation":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW/action/citation_signature","submit_replication":"https://pith.science/pith/7WR3KKHVY4QRWUES62EPS34PTW/action/replication_record"}},"created_at":"2026-05-18T00:29:41.753028+00:00","updated_at":"2026-05-18T00:29:41.753028+00:00"}