{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JP5IB7Z5JSSIMIYALW333ZLVLR","short_pith_number":"pith:JP5IB7Z5","schema_version":"1.0","canonical_sha256":"4bfa80ff3d4ca48623005db7bde5755c46db87aedf348ec5fff69cb125a02592","source":{"kind":"arxiv","id":"2307.15422","version":2},"attestation_state":"computed","paper":{"title":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Isabelle Guyon, Prasanna Balaprakash, Romain Egele, Yixuan Sun","submitted_at":"2023-07-28T09:14:41Z","abstract_excerpt":"Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models but can be computationally expensive. To reduce costs, Multi-fidelity HPO (MF-HPO) leverages intermediate accuracy levels in the learning process and discards low-performing models early on. We compared various representative MF-HPO methods against a simple baseline on classical benchmark data. The baseline involved discarding all models except the Top-K after training for only one epoch, followed by further training to select the best model. Surprisingly, this baseline achieved similar results to its counterp"},"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":"2307.15422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-28T09:14:41Z","cross_cats_sorted":[],"title_canon_sha256":"faa058493c943c5f0240c07d9952943baff8e4c3dc747f8a599a2c8d76b8ed2f","abstract_canon_sha256":"303894d1ba9956ee76c34a022466d0e03acefcc98bb30d598a3d6087f7b051d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:21.343124Z","signature_b64":"PSIMxhn9NwPiqLCkICHX5qSXrKX7tcghJ11xfUZQfPAZpSzLA6hkacMDUjAYhsOr/wGf8HZPVm8ID/c4MlQHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bfa80ff3d4ca48623005db7bde5755c46db87aedf348ec5fff69cb125a02592","last_reissued_at":"2026-07-05T06:54:21.342746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:21.342746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Isabelle Guyon, Prasanna Balaprakash, Romain Egele, Yixuan Sun","submitted_at":"2023-07-28T09:14:41Z","abstract_excerpt":"Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models but can be computationally expensive. To reduce costs, Multi-fidelity HPO (MF-HPO) leverages intermediate accuracy levels in the learning process and discards low-performing models early on. We compared various representative MF-HPO methods against a simple baseline on classical benchmark data. The baseline involved discarding all models except the Top-K after training for only one epoch, followed by further training to select the best model. Surprisingly, this baseline achieved similar results to its counterp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15422","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.15422/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2307.15422","created_at":"2026-07-05T06:54:21.342795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15422v2","created_at":"2026-07-05T06:54:21.342795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15422","created_at":"2026-07-05T06:54:21.342795+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP5IB7Z5JSSI","created_at":"2026-07-05T06:54:21.342795+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP5IB7Z5JSSIMIYA","created_at":"2026-07-05T06:54:21.342795+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP5IB7Z5","created_at":"2026-07-05T06:54:21.342795+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/JP5IB7Z5JSSIMIYALW333ZLVLR","json":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR.json","graph_json":"https://pith.science/api/pith-number/JP5IB7Z5JSSIMIYALW333ZLVLR/graph.json","events_json":"https://pith.science/api/pith-number/JP5IB7Z5JSSIMIYALW333ZLVLR/events.json","paper":"https://pith.science/paper/JP5IB7Z5"},"agent_actions":{"view_html":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR","download_json":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR.json","view_paper":"https://pith.science/paper/JP5IB7Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15422&json=true","fetch_graph":"https://pith.science/api/pith-number/JP5IB7Z5JSSIMIYALW333ZLVLR/graph.json","fetch_events":"https://pith.science/api/pith-number/JP5IB7Z5JSSIMIYALW333ZLVLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR/action/storage_attestation","attest_author":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR/action/author_attestation","sign_citation":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR/action/citation_signature","submit_replication":"https://pith.science/pith/JP5IB7Z5JSSIMIYALW333ZLVLR/action/replication_record"}},"created_at":"2026-07-05T06:54:21.342795+00:00","updated_at":"2026-07-05T06:54:21.342795+00:00"}