{"id":"W2963548849","doi":"10.1109/tit.2017.2788445","title":"Robustness to Unknown Error in Sparse Regularization","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Pacific Institute for the Mathematical Sciences; Alfred P. Sloan Foundation","keywords":"Robustness (evolution); Orthonormal basis; Compressed sensing; Mathematics; Bounded function; Quadratic growth; Quotient; Gaussian; Algorithm; A priori and a posteriori; Computer science; Mathematical optimization; Combinatorics","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":[0.0001647913,0.000113263,0.00009470581,0.0004083441,0.0000760916,0.00003933056,0.0001009543,0.00008387431,0.0001062915],"category_scores_gemma":[0.000006228701,0.0001193845,0.0000311711,0.000385557,0.0000350128,0.0005991436,8.019409e-7,0.0001240019,0.0001725943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008039735,"about_ca_system_score_gemma":0.00001230793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004375497,"about_ca_topic_score_gemma":0.00002093961,"domain_scores_codex":[0.9993901,0.00003145995,0.0002436835,0.0000696389,0.0001145348,0.00015059],"domain_scores_gemma":[0.9995919,0.00003117372,0.00002470557,0.0002225112,0.000082312,0.00004738151],"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":[0.0000582608,0.00001854667,8.09339e-7,0.000009542872,0.00001088711,4.83597e-7,0.0009979082,0.9404666,0.001037232,0.003413228,0.0006327404,0.05335372],"study_design_scores_gemma":[0.0004579751,0.0001377821,0.0001321755,0.0001736879,0.00001699427,0.00001055484,0.0002930368,0.5954883,0.3920411,0.00297959,0.007872714,0.0003960953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03091428,0.000002844356,0.9600461,0.00004240599,0.0005756443,0.0002081687,0.00000627708,0.000592553,0.007611798],"genre_scores_gemma":[0.9959617,0.000005952509,0.003528406,0.0002538588,0.00003888868,0.00003850923,0.000004917318,0.00001471685,0.0001530598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9650474,"threshold_uncertainty_score":0.4868358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01239149005046198,"score_gpt":0.2279077615430635,"score_spread":0.2155162714926015,"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."}}