{"id":"W3046037042","doi":"","title":"Beyond H-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Divergence (linguistics); Marginal distribution; Domain (mathematical analysis); USable; Matching (statistics); Computer science; Kullback–Leibler divergence; Perspective (graphical); Chain rule (probability); Mathematics; Information theory; Upper and lower bounds; Theoretical computer science; Mathematical optimization; Artificial intelligence; Statistics; Random variable; Regular conditional probability; Posterior probability; Bayesian probability; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004973246,0.0004861108,0.0004177981,0.0003006185,0.0004087455,0.0002301358,0.002018115,0.0002917286,0.0002023376],"category_scores_gemma":[0.00005669376,0.0005118913,0.0002110744,0.001145127,0.0002139209,0.000660488,0.001675224,0.0008790031,0.0004192784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001923268,"about_ca_system_score_gemma":0.0003838141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007311076,"about_ca_topic_score_gemma":0.00004060234,"domain_scores_codex":[0.9968078,0.0004874815,0.0002952566,0.001606817,0.0003124784,0.0004901289],"domain_scores_gemma":[0.9976921,0.0001814508,0.0004739351,0.001021959,0.0002712807,0.000359254],"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":[0.0001837195,0.00006962795,0.002363066,0.00006428466,0.0001587259,0.0007341538,0.004480113,0.2801538,0.00009915113,0.7095143,0.0003222183,0.001856839],"study_design_scores_gemma":[0.001102393,0.00025378,0.004336163,0.0001397168,0.0001179585,0.00001219227,0.002806786,0.6086342,0.00009336288,0.3783252,0.002996698,0.001181547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04953132,0.00009311225,0.9378505,0.0003172969,0.0007916049,0.000400801,0.00001973395,0.0004917146,0.01050386],"genre_scores_gemma":[0.9771507,0.0001628123,0.01954032,0.0003944706,0.0001337949,0.000002844709,0.00005214379,0.00003299868,0.002529866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9276195,"threshold_uncertainty_score":0.9997333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06600459547504262,"score_gpt":0.1885956435310878,"score_spread":0.1225910480560452,"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."}}