{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7GOBVDXMNET3X5ULW7IDVK7BLD","short_pith_number":"pith:7GOBVDXM","schema_version":"1.0","canonical_sha256":"f99c1a8eec6927bbf68bb7d03aabe158c0011655e94c527c6cbff961d95ba111","source":{"kind":"arxiv","id":"1806.04522","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning for Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Wenbo Gong, Yingzhen Li","submitted_at":"2018-06-12T13:50:59Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has become increasingly popular for simulating posterior samples in large-scale Bayesian modeling. However, existing SG-MCMC schemes are not tailored to any specific probabilistic model, even a simple modification of the underlying dynamical system requires significant physical intuition. This paper presents the first meta-learning algorithm that allows automated design for the underlying continuous dynamics of an SG-MCMC sampler. The learned sampler generalizes Hamiltonian dynamics with state-dependent drift and diffusion, enabling fast t"},"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":"1806.04522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T13:50:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89d625a1cd94dcd7240572c4c52dd538c3e0fdcbc748a65b1117fcd1f45d118f","abstract_canon_sha256":"4d04a0d0fb9119cad14e14e3dfefcc685d724f57ce3dda571ac1b57670b40f97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:33.524424Z","signature_b64":"vsjJWASdT8WcPxIgn7tpsJmrT25ky95m3FG4AK8KjxyeCKLCZSR6oQ/zavRZwbH5kJtbsOI6vEeRidCBdXkOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f99c1a8eec6927bbf68bb7d03aabe158c0011655e94c527c6cbff961d95ba111","last_reissued_at":"2026-05-18T00:13:33.523872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:33.523872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning for Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Wenbo Gong, Yingzhen Li","submitted_at":"2018-06-12T13:50:59Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has become increasingly popular for simulating posterior samples in large-scale Bayesian modeling. However, existing SG-MCMC schemes are not tailored to any specific probabilistic model, even a simple modification of the underlying dynamical system requires significant physical intuition. This paper presents the first meta-learning algorithm that allows automated design for the underlying continuous dynamics of an SG-MCMC sampler. The learned sampler generalizes Hamiltonian dynamics with state-dependent drift and diffusion, enabling fast t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04522","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":"1806.04522","created_at":"2026-05-18T00:13:33.523961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04522v1","created_at":"2026-05-18T00:13:33.523961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04522","created_at":"2026-05-18T00:13:33.523961+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GOBVDXMNET3","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GOBVDXMNET3X5UL","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GOBVDXM","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25710","citing_title":"Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23381","citing_title":"MCMC with Adaptive Principal-Component Transformation: Rotation-Invariant Universal Samplers for Bayesian Structural System Identification","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD","json":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD.json","graph_json":"https://pith.science/api/pith-number/7GOBVDXMNET3X5ULW7IDVK7BLD/graph.json","events_json":"https://pith.science/api/pith-number/7GOBVDXMNET3X5ULW7IDVK7BLD/events.json","paper":"https://pith.science/paper/7GOBVDXM"},"agent_actions":{"view_html":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD","download_json":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD.json","view_paper":"https://pith.science/paper/7GOBVDXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04522&json=true","fetch_graph":"https://pith.science/api/pith-number/7GOBVDXMNET3X5ULW7IDVK7BLD/graph.json","fetch_events":"https://pith.science/api/pith-number/7GOBVDXMNET3X5ULW7IDVK7BLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD/action/storage_attestation","attest_author":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD/action/author_attestation","sign_citation":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD/action/citation_signature","submit_replication":"https://pith.science/pith/7GOBVDXMNET3X5ULW7IDVK7BLD/action/replication_record"}},"created_at":"2026-05-18T00:13:33.523961+00:00","updated_at":"2026-05-18T00:13:33.523961+00:00"}