{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KYD5COEDETI7VOPCXTONSWSOCO","short_pith_number":"pith:KYD5COED","schema_version":"1.0","canonical_sha256":"5607d1388324d1fab9e2bcdcd95a4e13aee04a4b97975d4a739838f1c7d58778","source":{"kind":"arxiv","id":"1711.05560","version":1},"attestation_state":"computed","paper":{"title":"Variational Adaptive-Newton Method for Explorative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Didrik Nielsen, Mohammad Emtiyaz Khan, Voot Tangkaratt, Wu Lin, Zuozhu Liu","submitted_at":"2017-11-15T13:23:29Z","abstract_excerpt":"We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN estimates a distribution that can be used for exploration, but requires computations that are similar to continuous optimization methods. Our theoretical contribution reveals that VAN is a second-order method that unifies existing methods in distinct fields of continuous optimization, variational inference, and evolution strategies. Our experimental results show th"},"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":"1711.05560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-15T13:23:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8ed9dd03a25dccaafeb47bfeb7cd9047a1fb9a8726aee31041854c3db3ad7c5","abstract_canon_sha256":"ad5cc6c1bf03dc82db82a36480df41381eee0b37c4ed95e9116b8160e12c5b28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:29.521553Z","signature_b64":"AuaUE6tX6SH46FLorxzgsCMlhBl+7EGTxdSoYr60Od5MIHYtQeqskEhaC+hYHRfjYzwb2PZP2oHOl6IvTXzwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5607d1388324d1fab9e2bcdcd95a4e13aee04a4b97975d4a739838f1c7d58778","last_reissued_at":"2026-05-18T00:30:29.520871Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:29.520871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Adaptive-Newton Method for Explorative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Didrik Nielsen, Mohammad Emtiyaz Khan, Voot Tangkaratt, Wu Lin, Zuozhu Liu","submitted_at":"2017-11-15T13:23:29Z","abstract_excerpt":"We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN estimates a distribution that can be used for exploration, but requires computations that are similar to continuous optimization methods. Our theoretical contribution reveals that VAN is a second-order method that unifies existing methods in distinct fields of continuous optimization, variational inference, and evolution strategies. Our experimental results show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05560","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":"1711.05560","created_at":"2026-05-18T00:30:29.520988+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05560v1","created_at":"2026-05-18T00:30:29.520988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05560","created_at":"2026-05-18T00:30:29.520988+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYD5COEDETI7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYD5COEDETI7VOPC","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYD5COED","created_at":"2026-05-18T12:31:28.150371+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/KYD5COEDETI7VOPCXTONSWSOCO","json":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO.json","graph_json":"https://pith.science/api/pith-number/KYD5COEDETI7VOPCXTONSWSOCO/graph.json","events_json":"https://pith.science/api/pith-number/KYD5COEDETI7VOPCXTONSWSOCO/events.json","paper":"https://pith.science/paper/KYD5COED"},"agent_actions":{"view_html":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO","download_json":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO.json","view_paper":"https://pith.science/paper/KYD5COED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05560&json=true","fetch_graph":"https://pith.science/api/pith-number/KYD5COEDETI7VOPCXTONSWSOCO/graph.json","fetch_events":"https://pith.science/api/pith-number/KYD5COEDETI7VOPCXTONSWSOCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO/action/storage_attestation","attest_author":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO/action/author_attestation","sign_citation":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO/action/citation_signature","submit_replication":"https://pith.science/pith/KYD5COEDETI7VOPCXTONSWSOCO/action/replication_record"}},"created_at":"2026-05-18T00:30:29.520988+00:00","updated_at":"2026-05-18T00:30:29.520988+00:00"}