{"id":"W2979888181","doi":"10.48550/arxiv.1910.04153","title":"High Mutual Information in Representation Learning with Symmetric Variational Inference","year":2019,"lang":"en","type":"preprint","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":"University of Toronto","funders":"","keywords":"Mutual information; Parameterized complexity; Inference; Computer science; Conditional mutual information; Kullback–Leibler divergence; Encoder; Entropy (arrow of time); Information theory; Bounded function; Representation (politics); Joint probability distribution; Feature learning; Decoding methods; Boltzmann machine; Theoretical computer science; Artificial intelligence; Algorithm; Mathematics; Deep 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":[0.0003562958,0.0002152447,0.0002409014,0.0009750235,0.000109665,0.0002753057,0.0007515895,0.0001970932,0.00004764657],"category_scores_gemma":[0.0002323009,0.0002421313,0.00006070427,0.001668064,0.00003870733,0.001950642,0.0006257902,0.0008172033,0.000266231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002620575,"about_ca_system_score_gemma":0.0003435437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004226091,"about_ca_topic_score_gemma":0.00003181325,"domain_scores_codex":[0.9984518,0.0002342654,0.0002720533,0.0005744665,0.0002174745,0.0002499411],"domain_scores_gemma":[0.9983871,0.0003282708,0.0004675721,0.0004905636,0.0002454025,0.00008109186],"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":[0.00002821679,0.00001943202,0.02217922,0.00002164225,0.00001757831,0.00001747696,0.000634993,0.7415631,0.000001606105,0.2341047,0.00001151521,0.001400528],"study_design_scores_gemma":[0.0008534077,0.00006706543,0.05708434,0.0000674027,0.00001289136,0.000002417257,0.0002318103,0.9349887,0.000007852109,0.006042668,0.0003490663,0.0002923322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1613812,0.000005764299,0.834395,0.00006749888,0.000278108,0.0002482338,0.00000295722,0.0001384342,0.003482757],"genre_scores_gemma":[0.9914378,0.00003616166,0.007499993,0.00008190331,0.00002705458,0.000001886698,0.0001424251,0.000008291026,0.0007644903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8300565,"threshold_uncertainty_score":0.9873827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05126136843675917,"score_gpt":0.193380963464641,"score_spread":0.1421195950278819,"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."}}