{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MQO6JWCI4ZQB6D7DFACU3JPHGD","short_pith_number":"pith:MQO6JWCI","schema_version":"1.0","canonical_sha256":"641de4d848e6601f0fe328054da5e730d83692f5aa6e0a710bc0ac676c7b563d","source":{"kind":"arxiv","id":"1610.06664","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Gradient MCMC with Stale Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Nan Ding, Yizhe Zhang","submitted_at":"2016-10-21T04:18:11Z","abstract_excerpt":"Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popular to employ distributed systems, where stochastic gradients are computed based on some outdated parameters, yielding what are termed stale gradients. While stale gradients could be directly used in SG-MCMC, their impact on convergence properties has not been well studied. In this paper we develop theory to show that while the bias and MSE of an SG-MCMC algorithm depend on the "},"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":"1610.06664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-21T04:18:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c861b5c3d457e2f968c71c9b78aa517e80b283353c4304ec4634b3dbf4944a18","abstract_canon_sha256":"6d51ee198c6e02efa3f4781c40a4ad8000e4770bbd3ce31c75d2ecc6ac6f9956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:37.068209Z","signature_b64":"pwRgCjqmRIA6ajMsWHUNZg0fdNX3IqRcrHHgaF1/u/xBra8DWyYMBlPiq1ZIEqlEiy+wKv/MIlllLf5fSQHVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641de4d848e6601f0fe328054da5e730d83692f5aa6e0a710bc0ac676c7b563d","last_reissued_at":"2026-05-18T01:01:37.067583Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:37.067583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient MCMC with Stale Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Nan Ding, Yizhe Zhang","submitted_at":"2016-10-21T04:18:11Z","abstract_excerpt":"Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popular to employ distributed systems, where stochastic gradients are computed based on some outdated parameters, yielding what are termed stale gradients. While stale gradients could be directly used in SG-MCMC, their impact on convergence properties has not been well studied. In this paper we develop theory to show that while the bias and MSE of an SG-MCMC algorithm depend on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06664","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":"1610.06664","created_at":"2026-05-18T01:01:37.067685+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.06664v1","created_at":"2026-05-18T01:01:37.067685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06664","created_at":"2026-05-18T01:01:37.067685+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQO6JWCI4ZQB","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQO6JWCI4ZQB6D7D","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQO6JWCI","created_at":"2026-05-18T12:30:32.724797+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/MQO6JWCI4ZQB6D7DFACU3JPHGD","json":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD.json","graph_json":"https://pith.science/api/pith-number/MQO6JWCI4ZQB6D7DFACU3JPHGD/graph.json","events_json":"https://pith.science/api/pith-number/MQO6JWCI4ZQB6D7DFACU3JPHGD/events.json","paper":"https://pith.science/paper/MQO6JWCI"},"agent_actions":{"view_html":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD","download_json":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD.json","view_paper":"https://pith.science/paper/MQO6JWCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.06664&json=true","fetch_graph":"https://pith.science/api/pith-number/MQO6JWCI4ZQB6D7DFACU3JPHGD/graph.json","fetch_events":"https://pith.science/api/pith-number/MQO6JWCI4ZQB6D7DFACU3JPHGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD/action/storage_attestation","attest_author":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD/action/author_attestation","sign_citation":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD/action/citation_signature","submit_replication":"https://pith.science/pith/MQO6JWCI4ZQB6D7DFACU3JPHGD/action/replication_record"}},"created_at":"2026-05-18T01:01:37.067685+00:00","updated_at":"2026-05-18T01:01:37.067685+00:00"}