{"id":"W3035359320","doi":"10.48550/arxiv.2006.06587","title":"AdaS: Adaptive Scheduling of Stochastic Gradients","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generalization; Artificial intelligence; Adaptive optimization; Stochastic gradient descent; Scheduling (production processes); Machine learning; Artificial neural network; Mathematical optimization; Algorithm; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0001518652,0.0003566632,0.000481488,0.0003994549,0.00008968412,0.00005173622,0.002275352,0.0002480374,0.00001312364],"category_scores_gemma":[0.0001451917,0.0004408047,0.0002329806,0.0009429239,0.0001601402,0.0002244068,0.002454346,0.0005365215,0.00002185974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001843168,"about_ca_system_score_gemma":0.0002083495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004850057,"about_ca_topic_score_gemma":0.000002655034,"domain_scores_codex":[0.997904,0.00009914191,0.0003259304,0.001175679,0.0001710168,0.0003242463],"domain_scores_gemma":[0.9977045,0.00014116,0.0005352854,0.001062031,0.0003335176,0.0002234859],"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":[0.00002378001,0.00005985567,0.00006600098,0.00004124788,0.00007666361,0.0000455279,0.0003686213,0.5596314,0.0000261475,0.4395005,0.0000325758,0.0001276581],"study_design_scores_gemma":[0.0002956186,0.0001340528,0.00008134024,0.0001679677,0.00006443702,0.000002599246,0.00007417932,0.8831847,0.0001908111,0.1154554,0.000003230298,0.0003456998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01222241,0.0000442928,0.985643,0.00007385686,0.0004728997,0.0004783157,0.00002499838,0.0004240292,0.0006162504],"genre_scores_gemma":[0.9139169,0.00001241997,0.0858876,0.00005143527,0.00003268915,0.000002222137,0.000009494157,0.00002270056,0.00006455494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9016945,"threshold_uncertainty_score":0.9998044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09942448309067382,"score_gpt":0.1981458448133284,"score_spread":0.09872136172265454,"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."}}