{"id":"W2427484745","doi":"10.1017/jpr.2016.9","title":"Complexity bounds for Markov chain Monte Carlo algorithms via diffusion limits","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Markov chain Monte Carlo; Mathematics; Markov chain; Random walk; Algorithm; Limit (mathematics); Markov chain mixing time; Monte Carlo method; Metropolis–Hastings algorithm; Markov process; Metric (unit); Diffusion; Statistical physics; Applied mathematics; Markov model; Markov property; Statistics; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009228512,0.001374837,0.001765995,0.002770699,0.001584782,0.004126104,0.003041083,0.002431185,0.005139909],"category_scores_gemma":[0.07363269,0.0009479355,0.001842815,0.001815199,0.005222442,0.009337449,0.006004808,0.006407211,0.0006039209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004605483,"about_ca_system_score_gemma":0.002814565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002389832,"about_ca_topic_score_gemma":0.001683995,"domain_scores_codex":[0.9931658,0.002479157,0.0003577997,0.000938557,0.002541334,0.0005173892],"domain_scores_gemma":[0.896557,0.08978485,0.00344435,0.004153241,0.003924409,0.002136112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002106118,0.0001130946,0.001773593,0.0002728065,0.0001032476,0.0001153331,0.0002774321,0.2908209,0.002931523,0.6866986,0.001626889,0.01505592],"study_design_scores_gemma":[0.00001882712,0.00003047893,0.0001994064,0.00003704016,0.00001261144,0.00003757856,0.00001666677,0.7365854,0.0008178725,0.2615391,0.0006834607,0.00002155419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05929251,0.001830372,0.9215137,0.002680714,0.0001605777,0.0001706469,0.0002131773,0.0004624763,0.01367585],"genre_scores_gemma":[0.7974388,0.001975492,0.1917781,0.001072179,0.0004686159,0.0007501756,0.0004552462,0.0006194322,0.00544193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009228512,"threshold_uncertainty_score":0.04880559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09945098880932278,"score_gpt":0.3367509109275278,"score_spread":0.2372999221182051,"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."}}