{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:K4CRQCASFUONDISOPWHMWYZGKR","short_pith_number":"pith:K4CRQCAS","schema_version":"1.0","canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","source":{"kind":"arxiv","id":"1706.10031","version":1},"attestation_state":"computed","paper":{"title":"Neural Sequence Model Training via $\\alpha$-divergence Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii, Sotetsu Koyamada, Yuta Kikuchi","submitted_at":"2017-06-30T06:09:47Z","abstract_excerpt":"We propose a new neural sequence model training method in which the objective function is defined by $\\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\\alpha \\to 0$ and RL to $\\alpha \\to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\\alpha > 0$ outpe"},"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":"1706.10031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11f0f8d6e19a6b887e0720e4facffb93dd74504d77eebc0bbde5bab024509a25","abstract_canon_sha256":"13a22d503c5e9a23da277ab80ac190803bdbcb0233767ce67caa319e8383d041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:11.659540Z","signature_b64":"pY0leK0aoK9Th7+1gICEL0j+rPmEPR73tXHaTx33hJXw58+9LzBz2QnGnoyrqKI4ffrsWa8rD+6nITKKHC3ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","last_reissued_at":"2026-05-18T00:41:11.658826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:11.658826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Sequence Model Training via $\\alpha$-divergence Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii, Sotetsu Koyamada, Yuta Kikuchi","submitted_at":"2017-06-30T06:09:47Z","abstract_excerpt":"We propose a new neural sequence model training method in which the objective function is defined by $\\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\\alpha \\to 0$ and RL to $\\alpha \\to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\\alpha > 0$ outpe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.10031","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":"1706.10031","created_at":"2026-05-18T00:41:11.658924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.10031v1","created_at":"2026-05-18T00:41:11.658924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.10031","created_at":"2026-05-18T00:41:11.658924+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4CRQCASFUON","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4CRQCASFUONDISO","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4CRQCAS","created_at":"2026-05-18T12:31:24.725408+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/K4CRQCASFUONDISOPWHMWYZGKR","json":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR.json","graph_json":"https://pith.science/api/pith-number/K4CRQCASFUONDISOPWHMWYZGKR/graph.json","events_json":"https://pith.science/api/pith-number/K4CRQCASFUONDISOPWHMWYZGKR/events.json","paper":"https://pith.science/paper/K4CRQCAS"},"agent_actions":{"view_html":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR","download_json":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR.json","view_paper":"https://pith.science/paper/K4CRQCAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.10031&json=true","fetch_graph":"https://pith.science/api/pith-number/K4CRQCASFUONDISOPWHMWYZGKR/graph.json","fetch_events":"https://pith.science/api/pith-number/K4CRQCASFUONDISOPWHMWYZGKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/action/storage_attestation","attest_author":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/action/author_attestation","sign_citation":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/action/citation_signature","submit_replication":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/action/replication_record"}},"created_at":"2026-05-18T00:41:11.658924+00:00","updated_at":"2026-05-18T00:41:11.658924+00:00"}