{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EBCDQKJ3NT42PRLKTTZH7HFLMU","short_pith_number":"pith:EBCDQKJ3","schema_version":"1.0","canonical_sha256":"204438293b6cf9a7c56a9cf27f9cab651af5579438e78a5b855ec0e814bb0c7c","source":{"kind":"arxiv","id":"1902.03932","version":2},"attestation_state":"computed","paper":{"title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Changyou Chen, Chunyuan Li, Jianyi Zhang, Ruqi Zhang","submitted_at":"2019-02-11T15:03:30Z","abstract_excerpt":"The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We also prove non-asymptotic convergence of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the scalability and effectiveness of cyc"},"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":"1902.03932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-11T15:03:30Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ME","stat.ML"],"title_canon_sha256":"1786331b988e200c0da1185e88c2970c52aeab038f3032ee4096f7fca9d488a2","abstract_canon_sha256":"cd8f0b19b41da0e9d699431aea6ade84be5b4dfbb4a457b5a13f236d6ad5c87d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:00.852684Z","signature_b64":"H8l/Xxw4bjo3ZrEh3bubzkrMvumaDOZEIAS1g4eopnPfNFJLdiTy7ESc3LOZYIykllKf93sjmEIXSkovLeUFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"204438293b6cf9a7c56a9cf27f9cab651af5579438e78a5b855ec0e814bb0c7c","last_reissued_at":"2026-07-05T01:02:00.852271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:00.852271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Changyou Chen, Chunyuan Li, Jianyi Zhang, Ruqi Zhang","submitted_at":"2019-02-11T15:03:30Z","abstract_excerpt":"The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We also prove non-asymptotic convergence of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the scalability and effectiveness of cyc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03932","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.03932/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1902.03932","created_at":"2026-07-05T01:02:00.852326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03932v2","created_at":"2026-07-05T01:02:00.852326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03932","created_at":"2026-07-05T01:02:00.852326+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBCDQKJ3NT42","created_at":"2026-07-05T01:02:00.852326+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBCDQKJ3NT42PRLK","created_at":"2026-07-05T01:02:00.852326+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBCDQKJ3","created_at":"2026-07-05T01:02:00.852326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07556","citing_title":"Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning","ref_index":179,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU","json":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU.json","graph_json":"https://pith.science/api/pith-number/EBCDQKJ3NT42PRLKTTZH7HFLMU/graph.json","events_json":"https://pith.science/api/pith-number/EBCDQKJ3NT42PRLKTTZH7HFLMU/events.json","paper":"https://pith.science/paper/EBCDQKJ3"},"agent_actions":{"view_html":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU","download_json":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU.json","view_paper":"https://pith.science/paper/EBCDQKJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03932&json=true","fetch_graph":"https://pith.science/api/pith-number/EBCDQKJ3NT42PRLKTTZH7HFLMU/graph.json","fetch_events":"https://pith.science/api/pith-number/EBCDQKJ3NT42PRLKTTZH7HFLMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU/action/storage_attestation","attest_author":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU/action/author_attestation","sign_citation":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU/action/citation_signature","submit_replication":"https://pith.science/pith/EBCDQKJ3NT42PRLKTTZH7HFLMU/action/replication_record"}},"created_at":"2026-07-05T01:02:00.852326+00:00","updated_at":"2026-07-05T01:02:00.852326+00:00"}