{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TJEGAV5BPTTMTPIRZP3RSESNK5","short_pith_number":"pith:TJEGAV5B","schema_version":"1.0","canonical_sha256":"9a486057a17ce6c9bd11cbf719124d5770c4ed9c2db2180e4547cc180fcc0061","source":{"kind":"arxiv","id":"1507.01972","version":1},"attestation_state":"computed","paper":{"title":"Wasserstein Training of Boltzmann Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, Marco Cuturi","submitted_at":"2015-07-07T21:30:36Z","abstract_excerpt":"The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world. The default method to learn its parameters consists of minimizing the Kullback-Leibler (KL) divergence from training samples to the Boltzmann model. We propose in this work a novel approach for Boltzmann training which assumes that a meaningful metric between observations is given. This metric can be represented by the Wasserstein distance between distributions, for which we derive a gradient with respect to the model parameters. Minimization of "},"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":"1507.01972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-07T21:30:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8aec9f2daf34c9cc3c431f07902a2b97968b41675216579c471279b721b741ea","abstract_canon_sha256":"4cd4269f07dbe6451ad0c98990c8a0174a19177d7302ccca224193cc8426fbc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:10.563182Z","signature_b64":"MeuphsHOZnOShBLGyg/+xD9h/54i8ktZYXEHoHjFIt9cpjIHAOBVzBJtFIj6DUKjXAGVnBMaTRJxgPwBNWz9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a486057a17ce6c9bd11cbf719124d5770c4ed9c2db2180e4547cc180fcc0061","last_reissued_at":"2026-05-18T01:37:10.562631Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:10.562631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Training of Boltzmann Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, Marco Cuturi","submitted_at":"2015-07-07T21:30:36Z","abstract_excerpt":"The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world. The default method to learn its parameters consists of minimizing the Kullback-Leibler (KL) divergence from training samples to the Boltzmann model. We propose in this work a novel approach for Boltzmann training which assumes that a meaningful metric between observations is given. This metric can be represented by the Wasserstein distance between distributions, for which we derive a gradient with respect to the model parameters. Minimization of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01972","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":"1507.01972","created_at":"2026-05-18T01:37:10.562747+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.01972v1","created_at":"2026-05-18T01:37:10.562747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01972","created_at":"2026-05-18T01:37:10.562747+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJEGAV5BPTTM","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJEGAV5BPTTMTPIR","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJEGAV5B","created_at":"2026-05-18T12:29:42.218222+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/TJEGAV5BPTTMTPIRZP3RSESNK5","json":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5.json","graph_json":"https://pith.science/api/pith-number/TJEGAV5BPTTMTPIRZP3RSESNK5/graph.json","events_json":"https://pith.science/api/pith-number/TJEGAV5BPTTMTPIRZP3RSESNK5/events.json","paper":"https://pith.science/paper/TJEGAV5B"},"agent_actions":{"view_html":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5","download_json":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5.json","view_paper":"https://pith.science/paper/TJEGAV5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.01972&json=true","fetch_graph":"https://pith.science/api/pith-number/TJEGAV5BPTTMTPIRZP3RSESNK5/graph.json","fetch_events":"https://pith.science/api/pith-number/TJEGAV5BPTTMTPIRZP3RSESNK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5/action/storage_attestation","attest_author":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5/action/author_attestation","sign_citation":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5/action/citation_signature","submit_replication":"https://pith.science/pith/TJEGAV5BPTTMTPIRZP3RSESNK5/action/replication_record"}},"created_at":"2026-05-18T01:37:10.562747+00:00","updated_at":"2026-05-18T01:37:10.562747+00:00"}