{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QYKGJIL5B6VY7DZTUWEM6J4RG5","short_pith_number":"pith:QYKGJIL5","schema_version":"1.0","canonical_sha256":"861464a17d0fab8f8f33a588cf279137601e4d5de3d11e612032bd74bcc0553c","source":{"kind":"arxiv","id":"1901.08508","version":2},"attestation_state":"computed","paper":{"title":"Maximum Entropy Generators for Energy-Based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Anirudh Goyal, Rithesh Kumar, Sherjil Ozair, Yoshua Bengio","submitted_at":"2019-01-24T17:03:41Z","abstract_excerpt":"Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the energy function and an amortized approximate sampling mechanism using a neural generator network, which provides an efficient approximation of the log-likelihood gradient. The resulting objective requires maximizing entropy of the generated samples, which we perform using recently proposed nonparametric mutual information estimators. Finally, to stabilize the resulting adversarial game, we use a zero-centered gradient"},"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":"1901.08508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T17:03:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"42495be8070e4bc24ee89017eff66af37e97fd8bc92504c626d0210e7642ce84","abstract_canon_sha256":"c423122505f4016f6531bc4e196172b714ed5dc7da32139b350294e75a3a836f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:57.633036Z","signature_b64":"Ksn8xlF9eorz3EGfP7Oyps+I/vlo+28dcy6Wkq/3opMxIhJxnhpbZoMPAYsfVJ/gQqqaALGMIKEZm9X9CtonAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861464a17d0fab8f8f33a588cf279137601e4d5de3d11e612032bd74bcc0553c","last_reissued_at":"2026-05-17T23:44:57.632420Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:57.632420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy Generators for Energy-Based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Anirudh Goyal, Rithesh Kumar, Sherjil Ozair, Yoshua Bengio","submitted_at":"2019-01-24T17:03:41Z","abstract_excerpt":"Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the energy function and an amortized approximate sampling mechanism using a neural generator network, which provides an efficient approximation of the log-likelihood gradient. The resulting objective requires maximizing entropy of the generated samples, which we perform using recently proposed nonparametric mutual information estimators. Finally, to stabilize the resulting adversarial game, we use a zero-centered gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08508","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":"1901.08508","created_at":"2026-05-17T23:44:57.632517+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08508v2","created_at":"2026-05-17T23:44:57.632517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08508","created_at":"2026-05-17T23:44:57.632517+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYKGJIL5B6VY","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYKGJIL5B6VY7DZT","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYKGJIL5","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2301.09428","citing_title":"Explaining the effects of non-convergent sampling in the training of Energy-Based Models","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5","json":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5.json","graph_json":"https://pith.science/api/pith-number/QYKGJIL5B6VY7DZTUWEM6J4RG5/graph.json","events_json":"https://pith.science/api/pith-number/QYKGJIL5B6VY7DZTUWEM6J4RG5/events.json","paper":"https://pith.science/paper/QYKGJIL5"},"agent_actions":{"view_html":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5","download_json":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5.json","view_paper":"https://pith.science/paper/QYKGJIL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08508&json=true","fetch_graph":"https://pith.science/api/pith-number/QYKGJIL5B6VY7DZTUWEM6J4RG5/graph.json","fetch_events":"https://pith.science/api/pith-number/QYKGJIL5B6VY7DZTUWEM6J4RG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5/action/storage_attestation","attest_author":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5/action/author_attestation","sign_citation":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5/action/citation_signature","submit_replication":"https://pith.science/pith/QYKGJIL5B6VY7DZTUWEM6J4RG5/action/replication_record"}},"created_at":"2026-05-17T23:44:57.632517+00:00","updated_at":"2026-05-17T23:44:57.632517+00:00"}