{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EGGEKN26REVVIKMDYUUBV4HO5E","short_pith_number":"pith:EGGEKN26","schema_version":"1.0","canonical_sha256":"218c45375e892b542983c5281af0eee90cf0625b142e138a3ac6798a351414f2","source":{"kind":"arxiv","id":"1705.10823","version":2},"attestation_state":"computed","paper":{"title":"Accelerating Neural Architecture Search using Performance Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Bowen Baker, Nikhil Naik, Otkrist Gupta, Ramesh Raskar","submitted_at":"2017-05-30T19:00:53Z","abstract_excerpt":"Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can predict the final performance of partially trained model configurations using features based on network architectures, hyperparameters, and time-series validation performance data. We empirically show that our performance prediction models are much more effective than prominent Bayesian counterparts, are simpler to implement, and are faster to train. Our mode"},"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":"1705.10823","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T19:00:53Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"e3ba4f6d79f74b41d482f240f2636370c76c1dff68af17ac0e7be222283f3cbd","abstract_canon_sha256":"afd30a510259d4f42d7e32a297bb2384fb8eeecddb1cc976baeda881ef338249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:02.780782Z","signature_b64":"jWUYxsP/vGizpKC+kRUEwRmaLZmhJ1qi6QUZXxwe9qaKOnxmWyWEpMk3tQ6O86dJMYTR9vC3AbGeiipbrsUADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218c45375e892b542983c5281af0eee90cf0625b142e138a3ac6798a351414f2","last_reissued_at":"2026-05-18T00:31:02.780268Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:02.780268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Neural Architecture Search using Performance Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Bowen Baker, Nikhil Naik, Otkrist Gupta, Ramesh Raskar","submitted_at":"2017-05-30T19:00:53Z","abstract_excerpt":"Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can predict the final performance of partially trained model configurations using features based on network architectures, hyperparameters, and time-series validation performance data. We empirically show that our performance prediction models are much more effective than prominent Bayesian counterparts, are simpler to implement, and are faster to train. Our mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10823","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":"1705.10823","created_at":"2026-05-18T00:31:02.780362+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.10823v2","created_at":"2026-05-18T00:31:02.780362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10823","created_at":"2026-05-18T00:31:02.780362+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGGEKN26REVV","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGGEKN26REVVIKMD","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGGEKN26","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.12348","citing_title":"MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04648","citing_title":"EPNAS: Efficient Progressive Neural Architecture Search","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":138,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09290","citing_title":"From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07378","citing_title":"Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E","json":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E.json","graph_json":"https://pith.science/api/pith-number/EGGEKN26REVVIKMDYUUBV4HO5E/graph.json","events_json":"https://pith.science/api/pith-number/EGGEKN26REVVIKMDYUUBV4HO5E/events.json","paper":"https://pith.science/paper/EGGEKN26"},"agent_actions":{"view_html":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E","download_json":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E.json","view_paper":"https://pith.science/paper/EGGEKN26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.10823&json=true","fetch_graph":"https://pith.science/api/pith-number/EGGEKN26REVVIKMDYUUBV4HO5E/graph.json","fetch_events":"https://pith.science/api/pith-number/EGGEKN26REVVIKMDYUUBV4HO5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E/action/storage_attestation","attest_author":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E/action/author_attestation","sign_citation":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E/action/citation_signature","submit_replication":"https://pith.science/pith/EGGEKN26REVVIKMDYUUBV4HO5E/action/replication_record"}},"created_at":"2026-05-18T00:31:02.780362+00:00","updated_at":"2026-05-18T00:31:02.780362+00:00"}