{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00477769,0.00101708,0.001409313,0.0007706448,0.0005343864,0.001593248,0.00231832,0.001805992,0.004869852],"category_scores_gemma":[0.02986439,0.0007629967,0.0007206594,0.0005936338,0.002231735,0.003642829,0.003844832,0.004314477,0.0007882981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001915194,"about_ca_system_score_gemma":0.001672081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004013464,"about_ca_topic_score_gemma":0.003330691,"domain_scores_codex":[0.9987923,0.0004510101,0.00007105918,0.0002603395,0.0003137471,0.0001114525],"domain_scores_gemma":[0.9882205,0.009586841,0.0005412324,0.0008618585,0.0004111365,0.0003785249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001714372,0.0001532453,0.001050959,0.0001655259,0.00004135693,0.00008576197,0.0002121291,0.8150815,0.001977452,0.1238275,0.001018193,0.05621491],"study_design_scores_gemma":[0.00001133072,0.0000168129,0.00003345506,0.000008585859,0.000003325591,0.000008688882,0.000004567354,0.9750564,0.0003080707,0.02436401,0.0001820518,0.000002631437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02482432,0.0004148455,0.9700637,0.0005856227,0.00006454773,0.00006151521,0.00004057981,0.0005987738,0.003346057],"genre_scores_gemma":[0.6365427,0.0005975548,0.3560704,0.0006151868,0.0001354429,0.0003712132,0.0002212879,0.0005453698,0.004900882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004869852,"threshold_uncertainty_score":0.02526712,"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."}}