{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:2SXYCEFTESIYEHSCAZBRCRYBTP","short_pith_number":"pith:2SXYCEFT","schema_version":"1.0","canonical_sha256":"d4af8110b32491821e4206431147019be3866e769e9c4ddf74b2bac5cc4a0132","source":{"kind":"arxiv","id":"1301.3545","version":2},"attestation_state":"computed","paper":{"title":"Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Guillaume Desjardins, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-01-16T01:40:20Z","abstract_excerpt":"This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm belongs to the family of truncated Newton methods and exploits an efficient matrix-vector product to avoid explicitely storing the natural gradient metric $L$. This metric is shown to be the expected second derivative of the log-partition function (under the model distribution), or equivalently, the variance of the vector of partial derivatives of the energy function. We evaluate our method on the task of joint-train"},"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":"1301.3545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-16T01:40:20Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"f73ad516ae940591f5082d168e10243eee09675dc37cd251188d35b89f8975cb","abstract_canon_sha256":"33e252f3c176b9d15baeeddb0e0ea057346d12b8e67f4582875e43c42454e3f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:41.042994Z","signature_b64":"HPbk9CqlLXfykcNF6oJi6KmvpPqjyUFHam0UiYuDwQKQwIchcQgPMxfeVSvr6LAUBL45X+NBEih+F095ycUXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4af8110b32491821e4206431147019be3866e769e9c4ddf74b2bac5cc4a0132","last_reissued_at":"2026-05-18T03:30:41.042179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:41.042179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Guillaume Desjardins, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-01-16T01:40:20Z","abstract_excerpt":"This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm belongs to the family of truncated Newton methods and exploits an efficient matrix-vector product to avoid explicitely storing the natural gradient metric $L$. This metric is shown to be the expected second derivative of the log-partition function (under the model distribution), or equivalently, the variance of the vector of partial derivatives of the energy function. We evaluate our method on the task of joint-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3545","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":""},"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":"1301.3545","created_at":"2026-05-18T03:30:41.042312+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3545v2","created_at":"2026-05-18T03:30:41.042312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3545","created_at":"2026-05-18T03:30:41.042312+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SXYCEFTESIY","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SXYCEFTESIYEHSC","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SXYCEFT","created_at":"2026-05-18T12:27:32.513160+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/2SXYCEFTESIYEHSCAZBRCRYBTP","json":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP.json","graph_json":"https://pith.science/api/pith-number/2SXYCEFTESIYEHSCAZBRCRYBTP/graph.json","events_json":"https://pith.science/api/pith-number/2SXYCEFTESIYEHSCAZBRCRYBTP/events.json","paper":"https://pith.science/paper/2SXYCEFT"},"agent_actions":{"view_html":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP","download_json":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP.json","view_paper":"https://pith.science/paper/2SXYCEFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3545&json=true","fetch_graph":"https://pith.science/api/pith-number/2SXYCEFTESIYEHSCAZBRCRYBTP/graph.json","fetch_events":"https://pith.science/api/pith-number/2SXYCEFTESIYEHSCAZBRCRYBTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP/action/storage_attestation","attest_author":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP/action/author_attestation","sign_citation":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP/action/citation_signature","submit_replication":"https://pith.science/pith/2SXYCEFTESIYEHSCAZBRCRYBTP/action/replication_record"}},"created_at":"2026-05-18T03:30:41.042312+00:00","updated_at":"2026-05-18T03:30:41.042312+00:00"}