{"id":"W3208592040","doi":"","title":"Towards Noise-adaptive, Problem-adaptive Stochastic Gradient Descent","year":2021,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Noise (video); Stochastic gradient descent; Gradient descent; Computer science; Mathematical optimization; Control theory (sociology); Mathematics; Artificial intelligence; Artificial neural network","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","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.007092104,0.001355996,0.001300462,0.0006269049,0.001045699,0.00205082,0.004770165,0.000821688,0.0003513018],"category_scores_gemma":[0.002374003,0.001586239,0.00077643,0.002064793,0.00110323,0.0008989882,0.006379426,0.001845694,0.0001291697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225889,"about_ca_system_score_gemma":0.002164293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003590677,"about_ca_topic_score_gemma":0.001035625,"domain_scores_codex":[0.9824492,0.009290804,0.001799944,0.00319353,0.001777215,0.001489343],"domain_scores_gemma":[0.9801419,0.001983927,0.001685812,0.005080218,0.01018742,0.0009207152],"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":[0.00003273359,0.001989759,0.00007785486,0.0001839165,0.0002811288,0.00006092471,0.02244645,0.01029638,0.0005064447,0.9104847,0.0008207708,0.05281895],"study_design_scores_gemma":[0.001496796,0.00001190135,0.002744836,0.01084497,0.0003042916,0.0002530711,0.0006201462,0.9202482,0.02415117,0.03427124,0.002570438,0.002482989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002595477,0.002806808,0.9464206,0.01259743,0.001300866,0.002214757,0.0001082342,0.001016668,0.03093922],"genre_scores_gemma":[0.3146479,0.000520767,0.6754797,0.0002255329,0.00006047063,0.0005404603,0.0003277233,0.0001375322,0.008059921],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9099518,"threshold_uncertainty_score":0.9999191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02751191910310913,"score_gpt":0.2317008800844014,"score_spread":0.2041889609812923,"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."}}