{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QOBC7GZVHSU6YB2Z2FXGDEEHDA","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":"bea4632c154523da299fefd89d0e0469771949ffb55fcf2946990eaf4f0480b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-13T13:27:56Z","title_canon_sha256":"b33091204abfb4442b27a6746d0529f08263b3bacfcc76d29c8a5822bdb97b95"},"schema_version":"1.0","source":{"id":"1703.04379","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04379","created_at":"2026-05-18T00:33:21Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04379v4","created_at":"2026-05-18T00:33:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04379","created_at":"2026-05-18T00:33:21Z"},{"alias_kind":"pith_short_12","alias_value":"QOBC7GZVHSU6","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QOBC7GZVHSU6YB2Z","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QOBC7GZV","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:75248a8730a1729485dc55a5affcda1983a5416694206595820fef22250f6c79","target":"graph","created_at":"2026-05-18T00:33:21Z","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":"Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two consecutive phases to obtain better generalization performance: Bayesian sampling and stochastic optimization. The first phase is to explore the energy landscape and to capture the \"fat\" modes; and the second one is to fine-tune the parameter learned from the first phase. In the Bayesian learning phase, we apply continuous tempering and stochastic approximation into the Langev","authors_text":"Nanyang Ye, Rafal K. Mantiuk, Zhanxing Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-13T13:27:56Z","title":"Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04379","kind":"arxiv","version":4},"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:ae2058420ebccc482f1e8971815298f20a77bacdc2a6b41792c1de34d3fdb12b","target":"record","created_at":"2026-05-18T00:33:21Z","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":"bea4632c154523da299fefd89d0e0469771949ffb55fcf2946990eaf4f0480b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-13T13:27:56Z","title_canon_sha256":"b33091204abfb4442b27a6746d0529f08263b3bacfcc76d29c8a5822bdb97b95"},"schema_version":"1.0","source":{"id":"1703.04379","kind":"arxiv","version":4}},"canonical_sha256":"83822f9b353ca9ec0759d16e619087182a054fd5cf81b392ed5b5ee4fde5cb23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83822f9b353ca9ec0759d16e619087182a054fd5cf81b392ed5b5ee4fde5cb23","first_computed_at":"2026-05-18T00:33:21.146712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:21.146712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WV+0lx5SpjbPfjzWwnIgLdnrc78KYqdH8q8b8fAKrlaYiV8jCIeJDNK0V7o/w3z0cULUUSFVyGvZABgy2qwRDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:21.147273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.04379","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae2058420ebccc482f1e8971815298f20a77bacdc2a6b41792c1de34d3fdb12b","sha256:75248a8730a1729485dc55a5affcda1983a5416694206595820fef22250f6c79"],"state_sha256":"588bb6440800cd097114f5630889d3593c24327c8109675ebafeadb6dcb6221a"}