{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EJO2PUS2Z4QM7RTEZU23CSK4YT","short_pith_number":"pith:EJO2PUS2","schema_version":"1.0","canonical_sha256":"225da7d25acf20cfc664cd35b1495cc4d3da17844b511446931d726108852055","source":{"kind":"arxiv","id":"2101.07667","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Josif Grabocka, Martin Wistuba","submitted_at":"2021-01-19T15:00:39Z","abstract_excerpt":"Hyperparameter optimization (HPO) is a central pillar in the automation of machine learning solutions and is mainly performed via Bayesian optimization, where a parametric surrogate is learned to approximate the black box response function (e.g. validation error). Unfortunately, evaluating the response function is computationally intensive. As a remedy, earlier work emphasizes the need for transfer learning surrogates which learn to optimize hyperparameters for an algorithm from other tasks. In contrast to previous work, we propose to rethink HPO as a few-shot learning problem in which we trai"},"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":"2101.07667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-19T15:00:39Z","cross_cats_sorted":[],"title_canon_sha256":"06db76b57fe6861e987fb209b71cc06dddf332bfe04f8313443124199fb32865","abstract_canon_sha256":"f748762b99fb46868e758e04702456f846bc61bf9eec6442e97049b1edbc9e84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:00.161447Z","signature_b64":"cL5xUv+bQeQiWHxDTqALUdly3eWGVbmdGIu2Kji06uOdLPA7fsUYAYR+932VReKNsMfpgjY+9tH24yHnjX/zAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"225da7d25acf20cfc664cd35b1495cc4d3da17844b511446931d726108852055","last_reissued_at":"2026-07-05T02:08:00.161027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:00.161027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Josif Grabocka, Martin Wistuba","submitted_at":"2021-01-19T15:00:39Z","abstract_excerpt":"Hyperparameter optimization (HPO) is a central pillar in the automation of machine learning solutions and is mainly performed via Bayesian optimization, where a parametric surrogate is learned to approximate the black box response function (e.g. validation error). Unfortunately, evaluating the response function is computationally intensive. As a remedy, earlier work emphasizes the need for transfer learning surrogates which learn to optimize hyperparameters for an algorithm from other tasks. In contrast to previous work, we propose to rethink HPO as a few-shot learning problem in which we trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07667","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.07667/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":"2101.07667","created_at":"2026-07-05T02:08:00.161085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07667v1","created_at":"2026-07-05T02:08:00.161085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07667","created_at":"2026-07-05T02:08:00.161085+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJO2PUS2Z4QM","created_at":"2026-07-05T02:08:00.161085+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJO2PUS2Z4QM7RTE","created_at":"2026-07-05T02:08:00.161085+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJO2PUS2","created_at":"2026-07-05T02:08:00.161085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01328","citing_title":"Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT","json":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT.json","graph_json":"https://pith.science/api/pith-number/EJO2PUS2Z4QM7RTEZU23CSK4YT/graph.json","events_json":"https://pith.science/api/pith-number/EJO2PUS2Z4QM7RTEZU23CSK4YT/events.json","paper":"https://pith.science/paper/EJO2PUS2"},"agent_actions":{"view_html":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT","download_json":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT.json","view_paper":"https://pith.science/paper/EJO2PUS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07667&json=true","fetch_graph":"https://pith.science/api/pith-number/EJO2PUS2Z4QM7RTEZU23CSK4YT/graph.json","fetch_events":"https://pith.science/api/pith-number/EJO2PUS2Z4QM7RTEZU23CSK4YT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT/action/storage_attestation","attest_author":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT/action/author_attestation","sign_citation":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT/action/citation_signature","submit_replication":"https://pith.science/pith/EJO2PUS2Z4QM7RTEZU23CSK4YT/action/replication_record"}},"created_at":"2026-07-05T02:08:00.161085+00:00","updated_at":"2026-07-05T02:08:00.161085+00:00"}