{"id":"W3169578542","doi":"10.48550/arxiv.2011.00344","title":"A Distribution Dependent Analysis of Meta-Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Empirical risk minimization; Gaussian; Weighting; Context (archaeology); Covariance; Computer science; Transfer of learning; Meta learning (computer science); Statistical learning theory; Multi-task learning; Artificial intelligence; Mathematics; Algorithm; Representation (politics); Task (project management); Machine learning; Statistics; Support vector machine","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003421941,0.0002306914,0.0006445385,0.0003465437,0.0001162516,0.00009464408,0.001132588,0.0001622129,0.0001108055],"category_scores_gemma":[0.0001589283,0.0002562777,0.0007569682,0.002006056,0.00005525244,0.0002193851,0.001286066,0.0006153791,0.00003256215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221387,"about_ca_system_score_gemma":0.0001121064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001220975,"about_ca_topic_score_gemma":0.00002529512,"domain_scores_codex":[0.9981708,0.0003204609,0.0002634873,0.0008663931,0.0001643645,0.0002144911],"domain_scores_gemma":[0.9983576,0.0001762023,0.0005027961,0.0006284639,0.0001768421,0.000158111],"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":[0.00001386574,0.00003418985,0.002319411,0.00002601523,0.004548878,0.00007968428,0.0003426553,0.8714686,0.00003890792,0.1207853,0.00002512407,0.0003174113],"study_design_scores_gemma":[0.0001943303,0.00003341522,0.005921917,0.000009194125,0.005522693,5.78449e-7,0.0001315573,0.9837074,0.00007362122,0.003288287,0.000860405,0.0002565672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05670805,0.00006633947,0.9414879,0.000129627,0.0001167326,0.0001107905,0.00002695636,0.0001831708,0.001170404],"genre_scores_gemma":[0.997758,0.00006754442,0.001365312,0.00004797549,0.00001497882,7.643019e-7,0.0001467155,0.000008137103,0.0005905459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.94105,"threshold_uncertainty_score":0.999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1334583044850085,"score_gpt":0.2068033135328058,"score_spread":0.07334500904779723,"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."}}