{"id":"W3026366478","doi":"10.1016/j.spa.2020.05.004","title":"Optimal scaling of random-walk metropolis algorithms on general target distributions","year":2020,"lang":"en","type":"article","venue":"Stochastic Processes and their Applications","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Scaling; Random walk; Markov chain Monte Carlo; Bayesian probability; Metropolis–Hastings algorithm; Distribution (mathematics); Applied mathematics; Algorithm; Prior probability; Asymptotically optimal algorithm; Limit (mathematics); Mathematical optimization; Probability distribution; Statistical physics; Statistics; Mathematical analysis","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":[0.008869829,0.001742778,0.003013181,0.002086194,0.001419552,0.003782111,0.0033951,0.003212281,0.00620759],"category_scores_gemma":[0.047666,0.001712163,0.001190925,0.001871309,0.004105517,0.007367021,0.004115599,0.003644892,0.0007906657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00345541,"about_ca_system_score_gemma":0.002850389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002768862,"about_ca_topic_score_gemma":0.002463213,"domain_scores_codex":[0.996761,0.001816476,0.0001427225,0.0004750545,0.0005283244,0.0002764376],"domain_scores_gemma":[0.9702905,0.02408452,0.001261505,0.001657443,0.001623126,0.00108286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001415982,0.0001277332,0.0004467713,0.0001674378,0.00005520749,0.00005759617,0.0001392673,0.3414592,0.001186033,0.6396296,0.002496334,0.01409318],"study_design_scores_gemma":[0.00001560923,0.00001400988,0.0000735729,0.0000149121,0.000006621769,0.00001006218,0.00001127285,0.8609071,0.0002366071,0.1383027,0.0003962933,0.0000112546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0365722,0.001088869,0.9510859,0.001033543,0.000232099,0.0001347314,0.00009161097,0.0004027217,0.009358374],"genre_scores_gemma":[0.7057017,0.001965755,0.2730639,0.0006781716,0.0006259119,0.0008378332,0.0004056132,0.001143659,0.01557741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008869829,"threshold_uncertainty_score":0.04690868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04112606456423818,"score_gpt":0.3193986184460046,"score_spread":0.2782725538817664,"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."}}