{"id":"W3212640884","doi":"","title":"Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Generalization; Computer science; Benchmark (surveying); Artificial intelligence; Meta learning (computer science); Property (philosophy); Probably approximately correct learning; Norm (philosophy); Upper and lower bounds; Statistical learning theory; Theoretical computer science; Algorithm; Machine learning; Generalization error; Mathematics; Unsupervised learning; Task (project management)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002854197,0.0001098626,0.0001891148,0.0002805667,0.0002972663,0.0002733844,0.0003730288,0.00005609097,0.0002058614],"category_scores_gemma":[0.0001044806,0.0001209356,0.0002382185,0.001980933,0.00003769556,0.001734406,0.00008366392,0.00008550515,0.00003695773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004632635,"about_ca_system_score_gemma":0.00008519094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001210082,"about_ca_topic_score_gemma":0.00002214019,"domain_scores_codex":[0.9990907,0.0001769647,0.0001530064,0.0003144255,0.00007934189,0.0001855222],"domain_scores_gemma":[0.9989548,0.00008789394,0.0001361447,0.0003789364,0.0003266493,0.0001155551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004783547,0.00001687277,0.0007803605,0.000004836093,0.0003732047,0.000006594109,0.0004289368,0.4274031,0.0000177268,0.5704662,0.00003640534,0.0004610249],"study_design_scores_gemma":[0.0003275749,0.00004099184,0.0007445118,9.854318e-7,0.0008041388,0.000001821488,0.000300033,0.9695812,0.0001290505,0.01002467,0.01788402,0.0001609453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02706682,0.0000198617,0.9699796,0.0001096094,0.00007415737,0.00007049968,0.000002360539,0.0001454383,0.002531633],"genre_scores_gemma":[0.9854768,0.00002329467,0.01165572,0.0003449006,0.00001646974,0.000001890431,0.0001047835,0.000005196227,0.002370983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.95841,"threshold_uncertainty_score":0.4931611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07340860932113553,"score_gpt":0.198234698922775,"score_spread":0.1248260896016395,"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."}}