{"id":"W4406319221","doi":"10.48550/arxiv.2501.06148","title":"From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Mathematical Modeling in Engineering","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Narodowym Centrum Nauki; Deutsche Forschungsgemeinschaft; Nvidia","keywords":"Discrete time and continuous time; Diffusion; Training (meteorology); Computer science; Mathematics; Business; Statistics; Physics; Meteorology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001488294,0.0003901402,0.0005692143,0.000283232,0.000123158,0.0001940895,0.001387768,0.0001985617,0.00002739851],"category_scores_gemma":[0.0001548922,0.0004152581,0.000125066,0.0003268337,0.00009606394,0.0003619519,0.003442236,0.0003625255,0.00005889099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001161164,"about_ca_system_score_gemma":0.00007139335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001054682,"about_ca_topic_score_gemma":0.000004012194,"domain_scores_codex":[0.9980085,0.00006298783,0.0002668595,0.001085247,0.000125976,0.0004504491],"domain_scores_gemma":[0.998128,0.0005626949,0.0001280212,0.0008734559,0.00007450074,0.0002333272],"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":[0.00002641097,0.00006322157,0.0002016816,0.0002133686,0.0001647588,0.00006743465,0.007772056,0.9224233,0.001785307,0.06388906,0.00006994908,0.003323433],"study_design_scores_gemma":[0.000220041,0.00004086849,0.0001476939,0.0007594979,0.00005694059,0.000001375931,0.0002091884,0.9025619,0.00006832529,0.09539572,0.00007187947,0.0004665926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2757836,0.0000312017,0.7224508,0.000137729,0.0001821588,0.0002255417,0.00003888551,0.0002919151,0.0008581548],"genre_scores_gemma":[0.9215515,0.00002774045,0.07582867,0.0001319178,0.00009242599,0.000002181779,0.00001022006,0.00002010975,0.00233526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6466221,"threshold_uncertainty_score":0.9998299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05708389710966096,"score_gpt":0.212989379726284,"score_spread":0.155905482616623,"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."}}