{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008369274,0.0001083195,0.0001919626,0.000191365,0.0003388256,0.00004005339,0.00007505517,0.0000287508,0.00004705608],"category_scores_gemma":[0.000001904337,0.000116007,0.0001096865,0.0004876642,0.00002056919,0.00002787462,0.00003944998,0.00008644385,9.545727e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003598219,"about_ca_system_score_gemma":0.00001474087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005794181,"about_ca_topic_score_gemma":0.000002728408,"domain_scores_codex":[0.9993898,0.00001575959,0.0001357607,0.0001788,0.0001558831,0.000123963],"domain_scores_gemma":[0.9997158,0.00007698988,0.00003447776,0.00009706909,0.00003706208,0.00003857329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000251131,0.00001533468,0.0000533155,0.000003891136,0.0004694487,8.906587e-7,0.000113421,0.9792174,0.001034994,0.01009979,0.006668409,0.002297985],"study_design_scores_gemma":[0.0005720175,0.00001385453,0.0007704067,0.000001330064,0.0004692517,0.000003259437,0.00009829286,0.9748811,0.0003781194,0.0156577,0.006991546,0.0001631675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1006373,0.0006144828,0.8973176,0.0001904892,0.00005776957,0.0002214556,0.00005097308,0.0003099355,0.0005999656],"genre_scores_gemma":[0.9871756,0.00003480415,0.01166269,0.0002479625,0.00004272313,0.0001694667,0.0005634274,0.00001702792,0.00008627067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8865383,"threshold_uncertainty_score":0.473063,"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."}}