{"id":"W3169728738","doi":"10.1609/aaai.v36i7.20701","title":"Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Economic and Social Research Council; National Research Foundation of Korea; Seoul National University; National Research Foundation; Compute Canada; Ministry of Education; McMaster University","keywords":"Stochastic gradient descent; Resampling; Inference; Computer science; Leverage (statistics); Gradient descent; Mathematics; Algorithm; Artificial intelligence; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844858,0.0002801089,0.0003191819,0.0002393564,0.0005172051,0.0002085571,0.00167009,0.00004391737,0.00004283382],"category_scores_gemma":[0.0002788259,0.0002117124,0.00006704214,0.0009504562,0.0003541992,0.0003015059,0.0009440305,0.0004310423,0.000003309424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009809906,"about_ca_system_score_gemma":0.0001055856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004235245,"about_ca_topic_score_gemma":0.000008768707,"domain_scores_codex":[0.9976615,0.00003275936,0.0005339932,0.0006370518,0.0007529074,0.0003817559],"domain_scores_gemma":[0.9983855,0.0001669262,0.0004597007,0.0003262706,0.0005336916,0.0001279086],"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":[0.0003187623,0.0005484012,0.000215192,0.00004781359,0.00003408955,0.000001704588,0.003391189,0.1138576,0.004021682,0.8040226,0.00003224204,0.0735088],"study_design_scores_gemma":[0.0001295012,0.0006133175,0.0001171762,0.0001926814,0.00002409346,0.00003659646,0.0008542779,0.9244642,0.02072192,0.05252336,0.000005143736,0.0003177179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05351891,0.00002587009,0.9437989,0.001277838,0.0002143068,0.0007003358,0.00001078856,0.0001669065,0.0002861461],"genre_scores_gemma":[0.9663609,0.00001136031,0.0332676,0.0001672818,0.00002356613,0.0001096357,0.000001599155,0.00001706282,0.00004099985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.912842,"threshold_uncertainty_score":0.8633381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05517963036051056,"score_gpt":0.2658407778660295,"score_spread":0.210661147505519,"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."}}