{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QOBC7GZVHSU6YB2Z2FXGDEEHDA","short_pith_number":"pith:QOBC7GZV","schema_version":"1.0","canonical_sha256":"83822f9b353ca9ec0759d16e619087182a054fd5cf81b392ed5b5ee4fde5cb23","source":{"kind":"arxiv","id":"1703.04379","version":4},"attestation_state":"computed","paper":{"title":"Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nanyang Ye, Rafal K. Mantiuk, Zhanxing Zhu","submitted_at":"2017-03-13T13:27:56Z","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"},"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":"1703.04379","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-13T13:27:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b33091204abfb4442b27a6746d0529f08263b3bacfcc76d29c8a5822bdb97b95","abstract_canon_sha256":"bea4632c154523da299fefd89d0e0469771949ffb55fcf2946990eaf4f0480b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:21.147273Z","signature_b64":"WV+0lx5SpjbPfjzWwnIgLdnrc78KYqdH8q8b8fAKrlaYiV8jCIeJDNK0V7o/w3z0cULUUSFVyGvZABgy2qwRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83822f9b353ca9ec0759d16e619087182a054fd5cf81b392ed5b5ee4fde5cb23","last_reissued_at":"2026-05-18T00:33:21.146712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:21.146712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nanyang Ye, Rafal K. Mantiuk, Zhanxing Zhu","submitted_at":"2017-03-13T13:27:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04379","kind":"arxiv","version":4},"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":"1703.04379","created_at":"2026-05-18T00:33:21.146793+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04379v4","created_at":"2026-05-18T00:33:21.146793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04379","created_at":"2026-05-18T00:33:21.146793+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOBC7GZVHSU6","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOBC7GZVHSU6YB2Z","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOBC7GZV","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2110.12922","citing_title":"On quantitative Laplace-type convergence results for some exponential probability measures, with two applications","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA","json":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA.json","graph_json":"https://pith.science/api/pith-number/QOBC7GZVHSU6YB2Z2FXGDEEHDA/graph.json","events_json":"https://pith.science/api/pith-number/QOBC7GZVHSU6YB2Z2FXGDEEHDA/events.json","paper":"https://pith.science/paper/QOBC7GZV"},"agent_actions":{"view_html":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA","download_json":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA.json","view_paper":"https://pith.science/paper/QOBC7GZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04379&json=true","fetch_graph":"https://pith.science/api/pith-number/QOBC7GZVHSU6YB2Z2FXGDEEHDA/graph.json","fetch_events":"https://pith.science/api/pith-number/QOBC7GZVHSU6YB2Z2FXGDEEHDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA/action/storage_attestation","attest_author":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA/action/author_attestation","sign_citation":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA/action/citation_signature","submit_replication":"https://pith.science/pith/QOBC7GZVHSU6YB2Z2FXGDEEHDA/action/replication_record"}},"created_at":"2026-05-18T00:33:21.146793+00:00","updated_at":"2026-05-18T00:33:21.146793+00:00"}