{"id":"W1885448067","doi":"10.48550/arxiv.1506.04573","title":"A New PAC-Bayesian Perspective on Domain Adaptation","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian probability; Divergence (linguistics); Perspective (graphical); Computer science; Domain (mathematical analysis); Generalization; Upper and lower bounds; Domain adaptation; Measure (data warehouse); Adaptation (eye); Generalization error; Artificial intelligence; Focus (optics); Machine learning; Econometrics; Data mining; Mathematics; Psychology","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":[0.00802864,0.001664819,0.001865486,0.001609112,0.001276403,0.003523961,0.003655346,0.003347121,0.004331815],"category_scores_gemma":[0.02987731,0.001042822,0.001409625,0.001677889,0.004281828,0.008550262,0.006461176,0.007943493,0.001377834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002049721,"about_ca_system_score_gemma":0.001398342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001404664,"about_ca_topic_score_gemma":0.001008543,"domain_scores_codex":[0.9943776,0.002839691,0.0001679124,0.001108409,0.001225992,0.0002803483],"domain_scores_gemma":[0.9872967,0.008738092,0.0006487529,0.001690024,0.001157526,0.0004688889],"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":[0.0001135761,0.0001331472,0.001078165,0.0002824482,0.0001611245,0.0001674503,0.0005600052,0.2226148,0.003452529,0.6893627,0.005934106,0.0761399],"study_design_scores_gemma":[0.00001653233,0.00004895121,0.0002041948,0.00003839821,0.00002038462,0.0001110781,0.00004391491,0.5593764,0.001433204,0.4347237,0.003956509,0.0000267184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001985586,0.0003289114,0.994608,0.0006802689,0.00004143423,0.00002093258,0.00002885552,0.00007687361,0.002229136],"genre_scores_gemma":[0.4179685,0.001923442,0.5619158,0.002169537,0.001275309,0.0005358634,0.000445893,0.0005321295,0.01323356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00802864,"threshold_uncertainty_score":0.04246002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09015163841440388,"score_gpt":0.2134027382900402,"score_spread":0.1232510998756363,"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."}}