{"id":"W4377130721","doi":"10.48550/arxiv.2305.10634","title":"Modified Gauss-Newton Algorithms under Noise","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Institutes of Health; National Science Foundation","keywords":"Stylized fact; Gauss; Noise (video); Stochastic gradient descent; Convergence (economics); Algorithm; Applied mathematics; Quadratic equation; Gradient descent; Computer science; Newton's method; Mathematics; Mathematical optimization; Artificial intelligence; Nonlinear system; Artificial neural network; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002508038,0.0004036286,0.0003687111,0.0006046992,0.000165221,0.0001816085,0.002567643,0.0004091215,0.00001818954],"category_scores_gemma":[0.00005175982,0.0004864239,0.000229409,0.001093638,0.0001239598,0.0003472181,0.002989236,0.0005677621,0.0001964201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003263473,"about_ca_system_score_gemma":0.00023924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004096724,"about_ca_topic_score_gemma":0.00002441594,"domain_scores_codex":[0.9974971,0.0001011098,0.0002696407,0.001487511,0.0001802882,0.0004643119],"domain_scores_gemma":[0.9973254,0.0001509678,0.0002817104,0.001786872,0.0002341242,0.0002209661],"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":[0.000005662119,0.00004540305,0.00006468685,0.00002313623,0.00004756515,0.0001073871,0.0001100417,0.6251862,0.000009174647,0.3731759,0.001060082,0.0001648048],"study_design_scores_gemma":[0.0002583853,0.00003550017,0.0003488964,0.00006829958,0.00003554815,0.000003075702,0.00003471448,0.7879586,0.0001237026,0.2106361,0.00006748507,0.0004296717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005081934,0.00002177372,0.9890264,0.0004569955,0.001373843,0.0004687014,0.00002047076,0.002333045,0.00121678],"genre_scores_gemma":[0.960049,0.0001637648,0.03118171,0.0001767092,0.0001232234,0.000007141147,0.00005216169,0.00006374318,0.008182598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9578447,"threshold_uncertainty_score":0.9997587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1433337203683941,"score_gpt":0.2145114235177642,"score_spread":0.07117770314937008,"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."}}