{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TQJ5MGZGKBDGPD42FFATMFDKHV","short_pith_number":"pith:TQJ5MGZG","schema_version":"1.0","canonical_sha256":"9c13d61b265046678f9a294136146a3d78a8abdc98236b5b37ed491ad9fdfb11","source":{"kind":"arxiv","id":"1711.05307","version":2},"attestation_state":"computed","paper":{"title":"Neural Network Gradient Hamiltonian Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Andrew Holbrook, Babak Shahbaba, Lingge Li, Pierre Baldi","submitted_at":"2017-11-14T20:23:50Z","abstract_excerpt":"Hamiltonian Monte Carlo is a widely used algorithm for sampling from posterior distributions of complex Bayesian models. It can efficiently explore high-dimensional parameter spaces guided by simulated Hamiltonian flows. However, the algorithm requires repeated gradient calculations, and these computations become increasingly burdensome as data sets scale. We present a method to substantially reduce the computation burden by using a neural network to approximate the gradient. First, we prove that the proposed method still maintains convergence to the true distribution though the approximated g"},"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":"1711.05307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-11-14T20:23:50Z","cross_cats_sorted":[],"title_canon_sha256":"64fcdff2af1877df7796c5f94e424838bd181892aded342fa31483c610d24f9a","abstract_canon_sha256":"64811b4edfe5673e5663698b5f9059c607e44a7b31168b6696385af9cec802cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:44.440988Z","signature_b64":"+5OhOHm5gfbxFQtKVM/TnqRoaKGMPSHPw2BO8fi8Nrw5j61Rkwtn71QRK0WAzM91VWpb6KlbE9aY+PinyDOXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c13d61b265046678f9a294136146a3d78a8abdc98236b5b37ed491ad9fdfb11","last_reissued_at":"2026-05-17T23:47:44.440562Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:44.440562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Gradient Hamiltonian Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Andrew Holbrook, Babak Shahbaba, Lingge Li, Pierre Baldi","submitted_at":"2017-11-14T20:23:50Z","abstract_excerpt":"Hamiltonian Monte Carlo is a widely used algorithm for sampling from posterior distributions of complex Bayesian models. It can efficiently explore high-dimensional parameter spaces guided by simulated Hamiltonian flows. However, the algorithm requires repeated gradient calculations, and these computations become increasingly burdensome as data sets scale. We present a method to substantially reduce the computation burden by using a neural network to approximate the gradient. First, we prove that the proposed method still maintains convergence to the true distribution though the approximated g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05307","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":"1711.05307","created_at":"2026-05-17T23:47:44.440632+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05307v2","created_at":"2026-05-17T23:47:44.440632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05307","created_at":"2026-05-17T23:47:44.440632+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQJ5MGZGKBDG","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQJ5MGZGKBDGPD42","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQJ5MGZG","created_at":"2026-05-18T12:31:46.661854+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/TQJ5MGZGKBDGPD42FFATMFDKHV","json":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV.json","graph_json":"https://pith.science/api/pith-number/TQJ5MGZGKBDGPD42FFATMFDKHV/graph.json","events_json":"https://pith.science/api/pith-number/TQJ5MGZGKBDGPD42FFATMFDKHV/events.json","paper":"https://pith.science/paper/TQJ5MGZG"},"agent_actions":{"view_html":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV","download_json":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV.json","view_paper":"https://pith.science/paper/TQJ5MGZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05307&json=true","fetch_graph":"https://pith.science/api/pith-number/TQJ5MGZGKBDGPD42FFATMFDKHV/graph.json","fetch_events":"https://pith.science/api/pith-number/TQJ5MGZGKBDGPD42FFATMFDKHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV/action/storage_attestation","attest_author":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV/action/author_attestation","sign_citation":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV/action/citation_signature","submit_replication":"https://pith.science/pith/TQJ5MGZGKBDGPD42FFATMFDKHV/action/replication_record"}},"created_at":"2026-05-17T23:47:44.440632+00:00","updated_at":"2026-05-17T23:47:44.440632+00:00"}