{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01285545,0.001871315,0.002028325,0.001840164,0.001009629,0.002764958,0.003946816,0.003203924,0.004005063],"category_scores_gemma":[0.06986056,0.001275319,0.001963208,0.001372543,0.003558356,0.008859836,0.005338233,0.007547784,0.0006388217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002993499,"about_ca_system_score_gemma":0.002008386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001151598,"about_ca_topic_score_gemma":0.001111968,"domain_scores_codex":[0.9937075,0.003107708,0.0002014645,0.001117617,0.001482572,0.0003831589],"domain_scores_gemma":[0.9568332,0.03311825,0.001883444,0.004753578,0.002690807,0.0007207452],"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":[0.0001557823,0.0001080114,0.001818513,0.00027506,0.0002380837,0.0001373569,0.0002385905,0.523932,0.002617718,0.4265643,0.002461203,0.04145335],"study_design_scores_gemma":[0.00001073219,0.00005005643,0.000289785,0.00003441979,0.00002544444,0.00004359917,0.00001582131,0.8382397,0.0008260946,0.1595738,0.0008752905,0.00001516099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007284826,0.0004783202,0.9891853,0.0007925592,0.00003249529,0.00003281916,0.00004917769,0.0001679943,0.001976494],"genre_scores_gemma":[0.7374803,0.001619849,0.2490365,0.00113876,0.0004685593,0.0005747071,0.000425603,0.0006699153,0.008585811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285545,"threshold_uncertainty_score":0.06798697,"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."}}