{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:E4UDKRLQHNOKUAHLYQA2F2ZK6U","short_pith_number":"pith:E4UDKRLQ","canonical_record":{"source":{"id":"1803.11159","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-29T17:06:26Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"70b2d13a60c3b4e60e32a224cc5a05b6a497eb4340916a427edaf679b46611fb","abstract_canon_sha256":"34cfda0a7eef149f3d7f01c4e77b1c8c5f73a6e83df9b7d1118bf0f69cbed5aa"},"schema_version":"1.0"},"canonical_sha256":"27283545703b5caa00ebc401a2eb2af53420e0cdc2641188ec243c07aaa20da2","source":{"kind":"arxiv","id":"1803.11159","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11159","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11159v3","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11159","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"E4UDKRLQHNOK","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E4UDKRLQHNOKUAHL","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E4UDKRLQ","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:E4UDKRLQHNOKUAHLYQA2F2ZK6U","target":"record","payload":{"canonical_record":{"source":{"id":"1803.11159","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-29T17:06:26Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"70b2d13a60c3b4e60e32a224cc5a05b6a497eb4340916a427edaf679b46611fb","abstract_canon_sha256":"34cfda0a7eef149f3d7f01c4e77b1c8c5f73a6e83df9b7d1118bf0f69cbed5aa"},"schema_version":"1.0"},"canonical_sha256":"27283545703b5caa00ebc401a2eb2af53420e0cdc2641188ec243c07aaa20da2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:43.364771Z","signature_b64":"T40dwvwizEET7Iiv9gu+LmPy414Yp3fucdkNIjci1a+Ynx9MXaggZsMfQ+6SDLnxVmdrdRuzxqv/nPbTyesTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27283545703b5caa00ebc401a2eb2af53420e0cdc2641188ec243c07aaa20da2","last_reissued_at":"2026-05-17T23:42:43.364141Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:43.364141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.11159","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RnNCpsms8vU/sLYNgf+iLRW14HFUJW0MqdCu6nPDpHOkvSgzjpIHAFwDBjIWMBC5XZGizMxcnwGw28U7U6wDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:04:45.653537Z"},"content_sha256":"8be92edfea5050d3a15c6ceaa3a82e28a7b66189897bbbf78edfe85f37b382e8","schema_version":"1.0","event_id":"sha256:8be92edfea5050d3a15c6ceaa3a82e28a7b66189897bbbf78edfe85f37b382e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:E4UDKRLQHNOKUAHLYQA2F2ZK6U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Li, Jun Zhu, Shuyu Cheng, Tianyi Zhang, Zhize Li","submitted_at":"2018-03-29T17:06:26Z","abstract_excerpt":"Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to reduce the high variance of noisy stochastic gradients, Dubey et al. [2016] applied the standard variance reduction technique on stochastic gradient Langevin dynamics and obtained both theoretical and experimental improvements. In this paper, we apply the variance reduction tricks on Hamiltonian Mon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11159","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ctl/4lq9+IvWxIrzoqvvbqgwjURYNQFa9CerV+0j0vI0MECRZBZOWz8mEIetnc+t+P4Dliqgv2vUl570QbcQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:04:45.654228Z"},"content_sha256":"744aa3f28fcf415c793369b7f488dc4e6236a51405e30859ef4b8f215520d079","schema_version":"1.0","event_id":"sha256:744aa3f28fcf415c793369b7f488dc4e6236a51405e30859ef4b8f215520d079"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/bundle.json","state_url":"https://pith.science/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T16:04:45Z","links":{"resolver":"https://pith.science/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U","bundle":"https://pith.science/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/bundle.json","state":"https://pith.science/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4UDKRLQHNOKUAHLYQA2F2ZK6U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:E4UDKRLQHNOKUAHLYQA2F2ZK6U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34cfda0a7eef149f3d7f01c4e77b1c8c5f73a6e83df9b7d1118bf0f69cbed5aa","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-29T17:06:26Z","title_canon_sha256":"70b2d13a60c3b4e60e32a224cc5a05b6a497eb4340916a427edaf679b46611fb"},"schema_version":"1.0","source":{"id":"1803.11159","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11159","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11159v3","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11159","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"E4UDKRLQHNOK","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E4UDKRLQHNOKUAHL","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E4UDKRLQ","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:744aa3f28fcf415c793369b7f488dc4e6236a51405e30859ef4b8f215520d079","target":"graph","created_at":"2026-05-17T23:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to reduce the high variance of noisy stochastic gradients, Dubey et al. [2016] applied the standard variance reduction technique on stochastic gradient Langevin dynamics and obtained both theoretical and experimental improvements. In this paper, we apply the variance reduction tricks on Hamiltonian Mon","authors_text":"Jian Li, Jun Zhu, Shuyu Cheng, Tianyi Zhang, Zhize Li","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-29T17:06:26Z","title":"Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11159","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8be92edfea5050d3a15c6ceaa3a82e28a7b66189897bbbf78edfe85f37b382e8","target":"record","created_at":"2026-05-17T23:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"34cfda0a7eef149f3d7f01c4e77b1c8c5f73a6e83df9b7d1118bf0f69cbed5aa","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-29T17:06:26Z","title_canon_sha256":"70b2d13a60c3b4e60e32a224cc5a05b6a497eb4340916a427edaf679b46611fb"},"schema_version":"1.0","source":{"id":"1803.11159","kind":"arxiv","version":3}},"canonical_sha256":"27283545703b5caa00ebc401a2eb2af53420e0cdc2641188ec243c07aaa20da2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27283545703b5caa00ebc401a2eb2af53420e0cdc2641188ec243c07aaa20da2","first_computed_at":"2026-05-17T23:42:43.364141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:43.364141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T40dwvwizEET7Iiv9gu+LmPy414Yp3fucdkNIjci1a+Ynx9MXaggZsMfQ+6SDLnxVmdrdRuzxqv/nPbTyesTBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:43.364771Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.11159","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8be92edfea5050d3a15c6ceaa3a82e28a7b66189897bbbf78edfe85f37b382e8","sha256:744aa3f28fcf415c793369b7f488dc4e6236a51405e30859ef4b8f215520d079"],"state_sha256":"52a0eb60e226162881689f9be5fca404c6f60f167f5bc40e7d9369e9fdf9df1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0GS/kTnLImnrcSRHAPkm3mQLNpWnm2NrRhLEl06mhkTP4U17Z6EHaF+oCFzgDgW3GOWHX7XvA++EXCNgQwLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:04:45.657948Z","bundle_sha256":"b62948b4378a2f6dde37764dfdf21814908ac52dd38ec1849843272ac094d7a4"}}