{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:JLWHJLXFSQNYUVQBUVLWTN7CCW","short_pith_number":"pith:JLWHJLXF","canonical_record":{"source":{"id":"1709.01180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-04T22:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"eecf4dbfd416c4fbf7f77caacf8f469f73d3237c5856a809c625916d6f508350","abstract_canon_sha256":"2cce21d75dd179922f57d33ae20dab664a7a42221cba4aa368bb5fbfc7e259e1"},"schema_version":"1.0"},"canonical_sha256":"4aec74aee5941b8a5601a55769b7e215b293d9ba91637f26a5b94ad1fc04d793","source":{"kind":"arxiv","id":"1709.01180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01180","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01180v1","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01180","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"JLWHJLXFSQNY","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JLWHJLXFSQNYUVQB","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JLWHJLXF","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:JLWHJLXFSQNYUVQBUVLWTN7CCW","target":"record","payload":{"canonical_record":{"source":{"id":"1709.01180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-04T22:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"eecf4dbfd416c4fbf7f77caacf8f469f73d3237c5856a809c625916d6f508350","abstract_canon_sha256":"2cce21d75dd179922f57d33ae20dab664a7a42221cba4aa368bb5fbfc7e259e1"},"schema_version":"1.0"},"canonical_sha256":"4aec74aee5941b8a5601a55769b7e215b293d9ba91637f26a5b94ad1fc04d793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:00.736547Z","signature_b64":"NKJDg7K8ZqUJhErGWo3UH95F5wWYoxKGnoVmNyt0IcnI6Ie0kRPKwC32w8mWEOwOvfBsEReaMwa9WQVhOmUjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aec74aee5941b8a5601a55769b7e215b293d9ba91637f26a5b94ad1fc04d793","last_reissued_at":"2026-05-18T00:36:00.735992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:00.735992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.01180","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KQWqEj332pTyG0IC6QBJAvynzRkO56nydVcS2gl94lDUC0M6cKtlozd2Axu95ofsnRMuQ08sWSVtGspb5qXkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:26:48.625948Z"},"content_sha256":"77722f4d8ea8251357b266f5753ff8ea8ce40fa62b1dfe5ae185813ebd4b9c1c","schema_version":"1.0","event_id":"sha256:77722f4d8ea8251357b266f5753ff8ea8ce40fa62b1dfe5ae185813ebd4b9c1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:JLWHJLXFSQNYUVQBUVLWTN7CCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Lawrence Carin, Qinliang su, Wenlin Wang, Yizhe Zhang","submitted_at":"2017-09-04T22:11:24Z","abstract_excerpt":"Stochastic gradient Markov Chain Monte Carlo (SG-MCMC) has been developed as a flexible family of scalable Bayesian sampling algorithms. However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's convergence rate. In this paper, we prove that under a limited computational budget/time, a larger minibatch size leads to a faster decrease of the mean squared error bound (thus the fastest one corresponds to using full gradients), which motivates the necessity of variance reduction in SG-MCMC. Consequently, by borrowing ideas from stochastic optimization, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01180","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLZyrSHEQMHpcLwzJKmfM+N9YavWs8sjF8J/yOAvbRHd1K51WefFnFC63aO03Dp1d82MzCfiqScKb51emgSLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:26:48.626521Z"},"content_sha256":"5567af5b7d45b9908358210c209a671a3e3e1411a36f308712863a24e7b3145d","schema_version":"1.0","event_id":"sha256:5567af5b7d45b9908358210c209a671a3e3e1411a36f308712863a24e7b3145d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/bundle.json","state_url":"https://pith.science/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/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":"2026-05-30T08:26:48Z","links":{"resolver":"https://pith.science/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW","bundle":"https://pith.science/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/bundle.json","state":"https://pith.science/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLWHJLXFSQNYUVQBUVLWTN7CCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JLWHJLXFSQNYUVQBUVLWTN7CCW","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":"2cce21d75dd179922f57d33ae20dab664a7a42221cba4aa368bb5fbfc7e259e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-04T22:11:24Z","title_canon_sha256":"eecf4dbfd416c4fbf7f77caacf8f469f73d3237c5856a809c625916d6f508350"},"schema_version":"1.0","source":{"id":"1709.01180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01180","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01180v1","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01180","created_at":"2026-05-18T00:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"JLWHJLXFSQNY","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JLWHJLXFSQNYUVQB","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JLWHJLXF","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:5567af5b7d45b9908358210c209a671a3e3e1411a36f308712863a24e7b3145d","target":"graph","created_at":"2026-05-18T00:36:00Z","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":"Stochastic gradient Markov Chain Monte Carlo (SG-MCMC) has been developed as a flexible family of scalable Bayesian sampling algorithms. However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's convergence rate. In this paper, we prove that under a limited computational budget/time, a larger minibatch size leads to a faster decrease of the mean squared error bound (thus the fastest one corresponds to using full gradients), which motivates the necessity of variance reduction in SG-MCMC. Consequently, by borrowing ideas from stochastic optimization, ","authors_text":"Changyou Chen, Lawrence Carin, Qinliang su, Wenlin Wang, Yizhe Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-04T22:11:24Z","title":"A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01180","kind":"arxiv","version":1},"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":"sha256:77722f4d8ea8251357b266f5753ff8ea8ce40fa62b1dfe5ae185813ebd4b9c1c","target":"record","created_at":"2026-05-18T00:36:00Z","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":"2cce21d75dd179922f57d33ae20dab664a7a42221cba4aa368bb5fbfc7e259e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-04T22:11:24Z","title_canon_sha256":"eecf4dbfd416c4fbf7f77caacf8f469f73d3237c5856a809c625916d6f508350"},"schema_version":"1.0","source":{"id":"1709.01180","kind":"arxiv","version":1}},"canonical_sha256":"4aec74aee5941b8a5601a55769b7e215b293d9ba91637f26a5b94ad1fc04d793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aec74aee5941b8a5601a55769b7e215b293d9ba91637f26a5b94ad1fc04d793","first_computed_at":"2026-05-18T00:36:00.735992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:00.735992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NKJDg7K8ZqUJhErGWo3UH95F5wWYoxKGnoVmNyt0IcnI6Ie0kRPKwC32w8mWEOwOvfBsEReaMwa9WQVhOmUjBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:00.736547Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77722f4d8ea8251357b266f5753ff8ea8ce40fa62b1dfe5ae185813ebd4b9c1c","sha256:5567af5b7d45b9908358210c209a671a3e3e1411a36f308712863a24e7b3145d"],"state_sha256":"2a45f6995d96fe4443c36ac8c5f48fc0535f636ede3da9cb994c69894fb26f94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fK8fG06+oeFMuicfpQ+fmKZ9pmZYGZZIy1Hc/sOt+AvEnQMidVnARGsVWYp1Zfa0rrGOo94yjMIsPlRlyAS0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:26:48.629359Z","bundle_sha256":"b01f71482eaa3db13260e167bfae1461159fa52e8bfe0daf96d84934bc3a13d6"}}