{"id":"W2410679624","doi":"","title":"A Column Generation Bound Minimization Approach with PAC-Bayesian Generalization Guarantees","year":2016,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Generalization; Column (typography); Computer science; Minification; Bayesian probability; Column generation; Mathematical optimization; Artificial intelligence; Mathematics; Computer network","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":[0.0006481912,0.0001903139,0.0001991135,0.000231132,0.0001750887,0.0005311834,0.0003472546,0.0000851724,0.0005073851],"category_scores_gemma":[0.001601484,0.0001172984,0.00002601893,0.0002437891,0.0002600493,0.0002790185,0.00003571704,0.00007585336,0.00007549411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006076384,"about_ca_system_score_gemma":0.0001140701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002252116,"about_ca_topic_score_gemma":0.0001051912,"domain_scores_codex":[0.9976205,0.0001360415,0.0006004495,0.0005198132,0.0009223295,0.0002009058],"domain_scores_gemma":[0.9979913,0.0005539868,0.0002089702,0.0002495729,0.0008957926,0.0001003785],"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":[0.0001257651,0.00008330031,0.0001811722,0.000003189326,0.0000221099,0.000006461626,0.000331212,0.008332569,0.002404121,0.856364,0.001246513,0.1308996],"study_design_scores_gemma":[0.00008515993,0.000230111,0.0002063599,0.00004200347,0.00001337132,0.00001670641,0.0003772204,0.7912354,0.001618687,0.2054254,0.0005092438,0.000240344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003525013,0.00001216823,0.9922754,0.001102111,0.0004100405,0.0002000246,0.0001852709,0.00003867885,0.002251308],"genre_scores_gemma":[0.9374583,0.00009364321,0.0607516,0.0001344954,0.0002165494,0.00001976275,0.00007057962,0.00001459739,0.001240517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9339333,"threshold_uncertainty_score":0.5555511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2157938118567386,"score_gpt":0.3608432622986248,"score_spread":0.1450494504418862,"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."}}