{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7DE4Y3KGNLOT7UMKMBYN3M5GYF","short_pith_number":"pith:7DE4Y3KG","schema_version":"1.0","canonical_sha256":"f8c9cc6d466add3fd18a6070ddb3a6c16737b3808cd484ff2a01e5dba17c54c1","source":{"kind":"arxiv","id":"1908.10382","version":1},"attestation_state":"computed","paper":{"title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Nicolo Fusi, Rishit Sheth","submitted_at":"2019-08-27T18:02:11Z","abstract_excerpt":"In this paper we introduce Feature Gradients, a gradient-based search algorithm for feature selection. Our approach extends a recent result on the estimation of learnability in the sublinear data regime by showing that the calculation can be performed iteratively (i.e., in mini-batches) and in linear time and space with respect to both the number of features D and the sample size N . This, along with a discrete-to-continuous relaxation of the search domain, allows for an efficient, gradient-based search algorithm among feature subsets for very large datasets. Crucially, our algorithm is capabl"},"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":"1908.10382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-27T18:02:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c7053e491f2873c302351015e2028840860cc51247b3c32c3d3caf12aa92309","abstract_canon_sha256":"7bd3d283e7638da1a7fbbda10fddcca5f67c8b593a6348033e67478f3b04c2c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:16.713577Z","signature_b64":"z92XZgYLzc4MZQKzqcieBVXmgg/2gwhyNj7LKM0XCDSZOYvpncU7JgdodSwAc3KrfzndYoU/Cme3KwNZDmjCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c9cc6d466add3fd18a6070ddb3a6c16737b3808cd484ff2a01e5dba17c54c1","last_reissued_at":"2026-07-05T00:00:16.713125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:16.713125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Nicolo Fusi, Rishit Sheth","submitted_at":"2019-08-27T18:02:11Z","abstract_excerpt":"In this paper we introduce Feature Gradients, a gradient-based search algorithm for feature selection. Our approach extends a recent result on the estimation of learnability in the sublinear data regime by showing that the calculation can be performed iteratively (i.e., in mini-batches) and in linear time and space with respect to both the number of features D and the sample size N . This, along with a discrete-to-continuous relaxation of the search domain, allows for an efficient, gradient-based search algorithm among feature subsets for very large datasets. Crucially, our algorithm is capabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10382","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/1908.10382/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":"1908.10382","created_at":"2026-07-05T00:00:16.713183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10382v1","created_at":"2026-07-05T00:00:16.713183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10382","created_at":"2026-07-05T00:00:16.713183+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DE4Y3KGNLOT","created_at":"2026-07-05T00:00:16.713183+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DE4Y3KGNLOT7UMK","created_at":"2026-07-05T00:00:16.713183+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DE4Y3KG","created_at":"2026-07-05T00:00:16.713183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.21581","citing_title":"Make Both Ends Meet: A Synergistic Optimization Infrared Small Target Detection with Streamlined Computational Overhead","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF","json":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF.json","graph_json":"https://pith.science/api/pith-number/7DE4Y3KGNLOT7UMKMBYN3M5GYF/graph.json","events_json":"https://pith.science/api/pith-number/7DE4Y3KGNLOT7UMKMBYN3M5GYF/events.json","paper":"https://pith.science/paper/7DE4Y3KG"},"agent_actions":{"view_html":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF","download_json":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF.json","view_paper":"https://pith.science/paper/7DE4Y3KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10382&json=true","fetch_graph":"https://pith.science/api/pith-number/7DE4Y3KGNLOT7UMKMBYN3M5GYF/graph.json","fetch_events":"https://pith.science/api/pith-number/7DE4Y3KGNLOT7UMKMBYN3M5GYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF/action/storage_attestation","attest_author":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF/action/author_attestation","sign_citation":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF/action/citation_signature","submit_replication":"https://pith.science/pith/7DE4Y3KGNLOT7UMKMBYN3M5GYF/action/replication_record"}},"created_at":"2026-07-05T00:00:16.713183+00:00","updated_at":"2026-07-05T00:00:16.713183+00:00"}