{"id":"W2339007906","doi":"10.1109/tit.2016.2553147","title":"Arbitrarily Tight Bounds on Differential Entropy of Gaussian Mixtures","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential entropy; Gaussian; Upper and lower bounds; Mathematics; Entropy (arrow of time); Sequence (biology); Information theory; Gaussian process; Amplitude; Algorithm; Statistical physics; Applied mathematics; Mathematical analysis; Principle of maximum entropy; Maximum entropy probability distribution; Physics; Statistics; Quantum mechanics","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":[0.0002746693,0.0001511146,0.0001439059,0.0004165855,0.0001366558,0.0001055643,0.0004318634,0.0001085851,0.0002248168],"category_scores_gemma":[0.000009503793,0.0001025468,0.0001232976,0.0002111024,0.00009057698,0.001676366,0.00000248396,0.0001570129,0.000185423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005300068,"about_ca_system_score_gemma":0.00006571689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003458699,"about_ca_topic_score_gemma":0.000001262948,"domain_scores_codex":[0.9987972,0.0001446143,0.000407114,0.0001343249,0.0003499478,0.0001667341],"domain_scores_gemma":[0.9989638,0.0002036818,0.0001921232,0.0004808625,0.00008992686,0.00006957341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001555105,0.0001348863,0.000001135302,0.00001371554,0.00003672886,3.122776e-7,0.001905713,0.0001790568,0.006326208,0.8912531,0.0005204725,0.09947316],"study_design_scores_gemma":[0.0009936243,0.0004559055,0.0001965687,0.00009717597,0.00001464351,0.000006978536,0.00004209901,0.001586895,0.9256135,0.06565511,0.005062535,0.0002750251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00610829,0.000002566955,0.9849981,0.000746034,0.0004529113,0.0001833539,0.00002724558,0.0003266251,0.007154884],"genre_scores_gemma":[0.9956514,0.00001767376,0.00303456,0.0008436451,0.00001961157,0.00003805416,0.000002530537,0.000006676438,0.0003858478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9895431,"threshold_uncertainty_score":0.4181738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007034788668061615,"score_gpt":0.2246682134667528,"score_spread":0.2176334247986912,"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."}}