{"id":"W3209416948","doi":"10.48550/arxiv.2111.00062","title":"Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Hypergeometric distribution; Upper and lower bounds; Inversion (geology); Generalization; Mathematics; Margin (machine learning); Hypergeometric function; Combinatorics; Set (abstract data type); Algorithm; Discrete mathematics; Computer science; Statistics; Pure mathematics; Mathematical analysis; Machine learning","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":[0.0003646581,0.0002508364,0.0002442067,0.0003894806,0.0005803454,0.0004915071,0.001301963,0.0002157287,0.00001175042],"category_scores_gemma":[0.0001565624,0.0002348721,0.0002346173,0.001502315,0.00005874952,0.0003999659,0.001706348,0.0004530125,0.000003583373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002253137,"about_ca_system_score_gemma":0.0003263103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007134065,"about_ca_topic_score_gemma":0.00002380729,"domain_scores_codex":[0.998293,0.0001927331,0.0001742035,0.0008960937,0.0001213622,0.0003226157],"domain_scores_gemma":[0.9983076,0.0001588182,0.0002959093,0.0008677348,0.0002792579,0.00009072031],"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":[0.000008225958,0.00005482884,0.00350429,0.0001509697,0.00007423462,0.00004848174,0.0002601659,0.9743005,0.0004533955,0.01479133,0.0002171912,0.006136398],"study_design_scores_gemma":[0.0002660938,0.00003097046,0.0002073828,0.00004508595,0.00007154306,0.000004653492,0.0001267497,0.9963268,0.0002225702,0.001382718,0.001026351,0.0002890976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2817344,0.0001420164,0.7167492,0.0000978872,0.0008927418,0.0001726521,0.000003771945,0.000118124,0.00008918579],"genre_scores_gemma":[0.9748061,0.0001049239,0.02346303,0.0001602309,0.0002239621,0.00000111758,0.00004222065,0.00002124552,0.001177221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6932862,"threshold_uncertainty_score":0.9577807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07267578090149533,"score_gpt":0.2081383649835599,"score_spread":0.1354625840820645,"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."}}