{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NKRCPWR5DBV4I3UARZ3WOXUQJY","short_pith_number":"pith:NKRCPWR5","schema_version":"1.0","canonical_sha256":"6aa227da3d186bc46e808e77675e904e2d1d394126d9162210988e2995041188","source":{"kind":"arxiv","id":"1906.03139","version":1},"attestation_state":"computed","paper":{"title":"Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Erich Elsen, Karel Lenc, Karen Simonyan, Tom Schaul","submitted_at":"2019-06-07T14:52:19Z","abstract_excerpt":"In this work we show that Evolution Strategies (ES) are a viable method for learning non-differentiable parameters of large supervised models. ES are black-box optimization algorithms that estimate distributions of model parameters; however they have only been used for relatively small problems so far. We show that it is possible to scale ES to more complex tasks and models with millions of parameters. While using ES for differentiable parameters is computationally impractical (although possible), we show that a hybrid approach is practically feasible in the case where the model has both diffe"},"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":"1906.03139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-07T14:52:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"665c318a0dec873cf52fbb251e18898222a1d446b3f5c03f682d69d53b02b507","abstract_canon_sha256":"07dea57836cd1aba8dbafd6b40f6a07ec04cc90857af0406bf8fa9b9bde5ebb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:54.873843Z","signature_b64":"EkJ+eIWgFFY2VZfzS+/ZBDv13umdPBatjrwEv3qBYrYX0IETM8/HqOqbfEPDaaLuSbh1Ef/LY2BUKHRFe+w+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa227da3d186bc46e808e77675e904e2d1d394126d9162210988e2995041188","last_reissued_at":"2026-05-17T23:43:54.873104Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:54.873104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Erich Elsen, Karel Lenc, Karen Simonyan, Tom Schaul","submitted_at":"2019-06-07T14:52:19Z","abstract_excerpt":"In this work we show that Evolution Strategies (ES) are a viable method for learning non-differentiable parameters of large supervised models. ES are black-box optimization algorithms that estimate distributions of model parameters; however they have only been used for relatively small problems so far. We show that it is possible to scale ES to more complex tasks and models with millions of parameters. While using ES for differentiable parameters is computationally impractical (although possible), we show that a hybrid approach is practically feasible in the case where the model has both diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03139","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":"1906.03139","created_at":"2026-05-17T23:43:54.873206+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03139v1","created_at":"2026-05-17T23:43:54.873206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03139","created_at":"2026-05-17T23:43:54.873206+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKRCPWR5DBV4","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKRCPWR5DBV4I3UA","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKRCPWR5","created_at":"2026-05-18T12:33:24.271573+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/NKRCPWR5DBV4I3UARZ3WOXUQJY","json":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY.json","graph_json":"https://pith.science/api/pith-number/NKRCPWR5DBV4I3UARZ3WOXUQJY/graph.json","events_json":"https://pith.science/api/pith-number/NKRCPWR5DBV4I3UARZ3WOXUQJY/events.json","paper":"https://pith.science/paper/NKRCPWR5"},"agent_actions":{"view_html":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY","download_json":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY.json","view_paper":"https://pith.science/paper/NKRCPWR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03139&json=true","fetch_graph":"https://pith.science/api/pith-number/NKRCPWR5DBV4I3UARZ3WOXUQJY/graph.json","fetch_events":"https://pith.science/api/pith-number/NKRCPWR5DBV4I3UARZ3WOXUQJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY/action/storage_attestation","attest_author":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY/action/author_attestation","sign_citation":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY/action/citation_signature","submit_replication":"https://pith.science/pith/NKRCPWR5DBV4I3UARZ3WOXUQJY/action/replication_record"}},"created_at":"2026-05-17T23:43:54.873206+00:00","updated_at":"2026-05-17T23:43:54.873206+00:00"}