{"id":"W4386918690","doi":"10.1109/tit.2023.3318152","title":"An Analysis of Transformed Unadjusted Langevin Algorithm for Heavy-Tailed Sampling","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Algorithm; Sampling (signal processing); Computer science; Statistical physics; Langevin dynamics; Statistics; Mathematics; Physics; Telecommunications; Detector","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006184265,0.001038567,0.001288554,0.0007289654,0.0006648958,0.001894608,0.003044613,0.001810126,0.005462812],"category_scores_gemma":[0.03685905,0.000605174,0.000944405,0.0007310646,0.002688451,0.003767074,0.003146848,0.00369818,0.0006324331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002104199,"about_ca_system_score_gemma":0.003021346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002979508,"about_ca_topic_score_gemma":0.002702293,"domain_scores_codex":[0.9976324,0.0007851955,0.0001176092,0.0003674551,0.0008418068,0.0002555527],"domain_scores_gemma":[0.9804569,0.01526504,0.0008833229,0.001569208,0.001240552,0.0005849251],"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":[0.0003998276,0.000091496,0.002275408,0.0001951788,0.00007166619,0.0002131226,0.0002101757,0.6753014,0.006028784,0.2891962,0.001210019,0.02480676],"study_design_scores_gemma":[0.00001143716,0.00002631706,0.00008854723,0.000006965124,0.000004602542,0.00002230556,0.000008030705,0.9735694,0.0007794223,0.02531201,0.0001627073,0.000008249216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01841033,0.0001280776,0.9790668,0.0003338594,0.00003250873,0.00008042867,0.00006303353,0.0002858575,0.001599104],"genre_scores_gemma":[0.6301324,0.0004307335,0.3616867,0.0004643613,0.00009929552,0.0005334942,0.0004735207,0.0003626712,0.005816815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006184265,"threshold_uncertainty_score":0.0327059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02100305471321971,"score_gpt":0.2713301903682936,"score_spread":0.2503271356550739,"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."}}