{"id":"W3155603885","doi":"10.1016/j.acha.2022.08.003","title":"Generalization bounds for sparse random feature expansions","year":2022,"lang":"en","type":"article","venue":"Applied and Computational Harmonic Analysis","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Feature (linguistics); Generalization; Leverage (statistics); Mathematics; Computer science; Pattern recognition (psychology); Artificial intelligence; Algorithm; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006472928,0.002096506,0.001332722,0.001933085,0.000850639,0.001433418,0.002167115,0.001835806,0.004653511],"category_scores_gemma":[0.03797076,0.0006274819,0.001455227,0.001270519,0.003095982,0.006093263,0.004124914,0.005446208,0.001377331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002302385,"about_ca_system_score_gemma":0.001010557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00210365,"about_ca_topic_score_gemma":0.002234549,"domain_scores_codex":[0.9974483,0.0008607816,0.000115816,0.0004856962,0.0008085882,0.0002808929],"domain_scores_gemma":[0.9761163,0.01781814,0.001230371,0.002418216,0.00189958,0.0005173046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002305402,0.00008643568,0.001611074,0.0004614179,0.00009550156,0.0002124924,0.0003017941,0.422972,0.00837046,0.4861309,0.009442072,0.07008534],"study_design_scores_gemma":[0.000007303771,0.00003544984,0.000300862,0.00005981976,0.00001568595,0.00006575294,0.00002328785,0.8422516,0.001575732,0.153438,0.002203746,0.00002269262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01319093,0.001568638,0.9760318,0.001227086,0.0001091135,0.00005646489,0.0002625848,0.0004337668,0.007119605],"genre_scores_gemma":[0.6251493,0.005392737,0.3502524,0.001725406,0.0009700494,0.0009576748,0.001614404,0.001251412,0.01268662],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006472928,"threshold_uncertainty_score":0.03423256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01191770637777331,"score_gpt":0.2259281337119926,"score_spread":0.2140104273342192,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}