{"id":"W2963114935","doi":"","title":"Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields","year":2015,"lang":"en","type":"article","venue":"ANU Open Research (Australian National University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Convergence (economics); Computer science; CRFS; Sampling (signal processing); Algorithm; Sampling scheme; Conditional random field; Stochastic gradient descent; Mathematical optimization; Rate of convergence; Mathematics; Artificial intelligence; Estimator; Statistics; Artificial neural network; Key (lock)","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":[0.003804185,0.001313615,0.001856468,0.001333996,0.0008419959,0.0009189178,0.002957554,0.002002198,0.00416176],"category_scores_gemma":[0.01025037,0.001081025,0.001085919,0.001551979,0.001182104,0.002136381,0.00125343,0.002992438,0.001848636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001579491,"about_ca_system_score_gemma":0.002095805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00836732,"about_ca_topic_score_gemma":0.01213163,"domain_scores_codex":[0.9982561,0.000957105,0.00007897563,0.0003288875,0.0002757814,0.0001031617],"domain_scores_gemma":[0.995804,0.003016756,0.000176876,0.0004146592,0.0004777101,0.0001100876],"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":[0.0001760404,0.0001324001,0.0008559514,0.0001363472,0.00008458272,0.00008870154,0.0001165552,0.7649332,0.002787996,0.02751845,0.005744583,0.1974252],"study_design_scores_gemma":[0.000008611673,0.00001247165,0.00003566037,0.000004373654,0.000002888235,0.0000094308,0.000003150201,0.9936713,0.0003895044,0.005320758,0.0005372839,0.000004537925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002182105,0.00008540294,0.9961487,0.00006866379,0.00002285038,0.00004695377,0.00004115541,0.001107536,0.0002966778],"genre_scores_gemma":[0.1110181,0.0001466736,0.8848451,0.0002379114,0.00007353469,0.0004214539,0.000644881,0.0005918771,0.002020347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00836732,"threshold_uncertainty_score":0.02011871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2458712651436055,"score_gpt":0.4074290261833877,"score_spread":0.1615577610397822,"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."}}