{"id":"W4407639540","doi":"10.1109/tit.2025.3541181","title":"Analysis of the Rate of Convergence of an Over-Parametrized Deep Neural Network Estimate Learned by Gradient Descent","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gradient descent; Convergence (economics); Artificial neural network; Computer science; Rate of convergence; Deep neural networks; Stochastic gradient descent; Artificial intelligence; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01194403,0.002565296,0.001857132,0.001260406,0.0007382576,0.001664314,0.002754241,0.003192137,0.002785615],"category_scores_gemma":[0.08341106,0.001107334,0.001134499,0.0009648744,0.002358829,0.003435332,0.003415609,0.004518321,0.0007448089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002394418,"about_ca_system_score_gemma":0.002008594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007223125,"about_ca_topic_score_gemma":0.0043633,"domain_scores_codex":[0.9972783,0.001334026,0.0001714387,0.0004090271,0.0005826807,0.0002246167],"domain_scores_gemma":[0.9409907,0.04779469,0.002902318,0.002992239,0.00455335,0.0007666176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006058013,0.00006945463,0.004120342,0.0004926623,0.0002084171,0.0004085697,0.0002375558,0.9262398,0.004931089,0.03001485,0.002423445,0.03024792],"study_design_scores_gemma":[0.000009833007,0.00005767502,0.000528124,0.0000526385,0.00001888729,0.00009284006,0.00002166461,0.9929132,0.00226169,0.003649342,0.0003751251,0.00001895975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08330642,0.002972256,0.9063237,0.001557554,0.0001508383,0.0001431404,0.0003427855,0.001255295,0.003947878],"genre_scores_gemma":[0.7805066,0.002563685,0.2023048,0.0006176732,0.0001851716,0.0006868584,0.001658469,0.002110016,0.009366662],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01194403,"threshold_uncertainty_score":0.0631668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00809871770870112,"score_gpt":0.2539479325295855,"score_spread":0.2458492148208843,"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."}}