{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:Y5GTVYFO25YL5P3VUHHZ7US4KV","short_pith_number":"pith:Y5GTVYFO","schema_version":"1.0","canonical_sha256":"c74d3ae0aed770bebf75a1cf9fd25c555d742db26addb869edf485148d448f16","source":{"kind":"arxiv","id":"1012.3476","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Parallel Tempering for Stochastic Maximum Likelihood Learning of RBMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Guillaume Desjardins, Yoshua Bengio","submitted_at":"2010-12-15T21:23:09Z","abstract_excerpt":"Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, because of the intractibility of their partition function. The maximum likelihood gradient requires a very robust sampler which can accurately sample from the model despite the loss of ergodicity often incurred during learning. While using Parallel Tempering in the negative phase of Stochastic Maximum Likelihood (SML-PT) helps address the issue, it imposes a trade-off between computational complexity and high ergodicity"},"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":"1012.3476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2010-12-15T21:23:09Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"70758de33b12130110f0f422e098c69cda91b93a864e32cc91864f48e349d7d1","abstract_canon_sha256":"0b33dad3751a0e55e408a017ffcd55d8ac209b3ec06f02b28e7a617d69df4a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:33:06.684223Z","signature_b64":"OoO3znHEqNeBpVgW2uZI0uSOVc3yPNdWciMINe965NNSadW4edJ5ZJaK1a+rLb6cmhqdh3n+VIvD7kFfi3yUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c74d3ae0aed770bebf75a1cf9fd25c555d742db26addb869edf485148d448f16","last_reissued_at":"2026-05-18T04:33:06.683576Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:33:06.683576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Parallel Tempering for Stochastic Maximum Likelihood Learning of RBMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Guillaume Desjardins, Yoshua Bengio","submitted_at":"2010-12-15T21:23:09Z","abstract_excerpt":"Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, because of the intractibility of their partition function. The maximum likelihood gradient requires a very robust sampler which can accurately sample from the model despite the loss of ergodicity often incurred during learning. While using Parallel Tempering in the negative phase of Stochastic Maximum Likelihood (SML-PT) helps address the issue, it imposes a trade-off between computational complexity and high ergodicity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.3476","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":"1012.3476","created_at":"2026-05-18T04:33:06.683677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1012.3476v1","created_at":"2026-05-18T04:33:06.683677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.3476","created_at":"2026-05-18T04:33:06.683677+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5GTVYFO25YL","created_at":"2026-05-18T12:26:17.028572+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5GTVYFO25YL5P3V","created_at":"2026-05-18T12:26:17.028572+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5GTVYFO","created_at":"2026-05-18T12:26:17.028572+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/Y5GTVYFO25YL5P3VUHHZ7US4KV","json":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV.json","graph_json":"https://pith.science/api/pith-number/Y5GTVYFO25YL5P3VUHHZ7US4KV/graph.json","events_json":"https://pith.science/api/pith-number/Y5GTVYFO25YL5P3VUHHZ7US4KV/events.json","paper":"https://pith.science/paper/Y5GTVYFO"},"agent_actions":{"view_html":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV","download_json":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV.json","view_paper":"https://pith.science/paper/Y5GTVYFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1012.3476&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5GTVYFO25YL5P3VUHHZ7US4KV/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5GTVYFO25YL5P3VUHHZ7US4KV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV/action/storage_attestation","attest_author":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV/action/author_attestation","sign_citation":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV/action/citation_signature","submit_replication":"https://pith.science/pith/Y5GTVYFO25YL5P3VUHHZ7US4KV/action/replication_record"}},"created_at":"2026-05-18T04:33:06.683677+00:00","updated_at":"2026-05-18T04:33:06.683677+00:00"}