{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IYBRSUMLWQCBRY3BC735FABZ5R","short_pith_number":"pith:IYBRSUML","schema_version":"1.0","canonical_sha256":"460319518bb40418e36117f7d28039ec46499ea812101382de5a46b6ab7f39b6","source":{"kind":"arxiv","id":"1711.09268","version":3},"attestation_state":"computed","paper":{"title":"Generalizing Hamiltonian Monte Carlo with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Levy, Jascha Sohl-Dickstein, Matthew D. Hoffman","submitted_at":"2017-11-25T18:08:02Z","abstract_excerpt":"We present a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution. Our method generalizes Hamiltonian Monte Carlo and is trained to maximize expected squared jumped distance, a proxy for mixing speed. We demonstrate large empirical gains on a collection of simple but challenging distributions, for instance achieving a 106x improvement in effective sample size in one case, and mixing when standard HMC makes no measurable progress in a second. Finally, we show quantitative and qualitati"},"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":"1711.09268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-25T18:08:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f6446e3039eec64c14dc0b3e56f76b1b6ea646b25aa5cbce72c58ddfe9b74185","abstract_canon_sha256":"9bd273996321ff3319357a8457352f168dc8c8b9561981e7c27fe22b56099db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:02.630044Z","signature_b64":"/kW3rfrG/qKrU2V2QxxdduRY2iDQzUaOF66fnojswtGXXb/xfGnNu6dbL2xDnI8rY2psQBkkWynUofyErKyXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460319518bb40418e36117f7d28039ec46499ea812101382de5a46b6ab7f39b6","last_reissued_at":"2026-05-18T00:22:02.629475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:02.629475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Hamiltonian Monte Carlo with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Levy, Jascha Sohl-Dickstein, Matthew D. Hoffman","submitted_at":"2017-11-25T18:08:02Z","abstract_excerpt":"We present a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution. Our method generalizes Hamiltonian Monte Carlo and is trained to maximize expected squared jumped distance, a proxy for mixing speed. We demonstrate large empirical gains on a collection of simple but challenging distributions, for instance achieving a 106x improvement in effective sample size in one case, and mixing when standard HMC makes no measurable progress in a second. Finally, we show quantitative and qualitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09268","kind":"arxiv","version":3},"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":"1711.09268","created_at":"2026-05-18T00:22:02.629585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09268v3","created_at":"2026-05-18T00:22:02.629585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09268","created_at":"2026-05-18T00:22:02.629585+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYBRSUMLWQCB","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYBRSUMLWQCBRY3B","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYBRSUML","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2010.02502","citing_title":"Denoising Diffusion Implicit Models","ref_index":12,"is_internal_anchor":true},{"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":2,"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":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R","json":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R.json","graph_json":"https://pith.science/api/pith-number/IYBRSUMLWQCBRY3BC735FABZ5R/graph.json","events_json":"https://pith.science/api/pith-number/IYBRSUMLWQCBRY3BC735FABZ5R/events.json","paper":"https://pith.science/paper/IYBRSUML"},"agent_actions":{"view_html":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R","download_json":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R.json","view_paper":"https://pith.science/paper/IYBRSUML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09268&json=true","fetch_graph":"https://pith.science/api/pith-number/IYBRSUMLWQCBRY3BC735FABZ5R/graph.json","fetch_events":"https://pith.science/api/pith-number/IYBRSUMLWQCBRY3BC735FABZ5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R/action/storage_attestation","attest_author":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R/action/author_attestation","sign_citation":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R/action/citation_signature","submit_replication":"https://pith.science/pith/IYBRSUMLWQCBRY3BC735FABZ5R/action/replication_record"}},"created_at":"2026-05-18T00:22:02.629585+00:00","updated_at":"2026-05-18T00:22:02.629585+00:00"}