{"id":"W3035691313","doi":"","title":"A simpler approach to accelerated optimization: iterative averaging meets optimism","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Optimization Algorithms Research","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematical optimization; Computer science; Control theory (sociology); Mathematics; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002398564,0.0003000999,0.0003031606,0.000247837,0.0002287178,0.0003563628,0.0005920699,0.00008411641,0.003043177],"category_scores_gemma":[0.001820715,0.0002919978,0.00007320203,0.0005015691,0.00003896749,0.0003600531,0.0002631813,0.0007739323,0.0001416983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001265788,"about_ca_system_score_gemma":0.00009179366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009345677,"about_ca_topic_score_gemma":9.67352e-7,"domain_scores_codex":[0.9975895,0.000215216,0.0004324713,0.0006214135,0.0008052846,0.0003361545],"domain_scores_gemma":[0.9983369,0.0002313582,0.0001852524,0.0001831947,0.0007595026,0.0003038158],"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":[0.0001258058,0.00008951168,0.00009209723,0.00001531446,0.00007192991,0.00001418503,0.002314246,0.9353582,0.0002104337,0.05936586,0.0003932523,0.001949129],"study_design_scores_gemma":[0.0007537237,0.0001335581,0.00001345475,0.00004351161,0.000007224221,0.000009303593,0.0003021441,0.9937548,0.0002565004,0.0009934254,0.003431874,0.0003004817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005732864,0.000009387594,0.9092739,0.01286121,0.00009858417,0.0004442951,0.00002650936,0.0003046463,0.07640823],"genre_scores_gemma":[0.5382953,0.00002699244,0.4573951,0.001825394,0.0002066352,0.00008071268,0.0002282752,0.00007054942,0.001871061],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.537722,"threshold_uncertainty_score":0.9999532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1987136704412686,"score_gpt":0.4037736806013445,"score_spread":0.2050600101600759,"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."}}