{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004412,0.0001018988,0.0002286253,0.0002465921,0.0001429768,0.00002583689,0.0005625877,0.00004476853,0.00002633953],"category_scores_gemma":[0.000009100393,0.00007847592,0.0001951742,0.002785057,0.0001211668,0.0005375411,0.000006776752,0.0001202136,0.000001497571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002323772,"about_ca_system_score_gemma":0.00003326026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003784367,"about_ca_topic_score_gemma":0.00001347522,"domain_scores_codex":[0.9988506,0.0001687604,0.0005639927,0.0001167142,0.000162152,0.0001377406],"domain_scores_gemma":[0.9986055,0.0002734541,0.0003817906,0.0005674385,0.0001330673,0.00003867575],"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":[0.00006183809,0.00008577992,0.00004867352,0.00001942667,0.0001558562,2.109502e-8,0.0002502741,0.9312463,0.0005963093,0.0297534,0.00004028229,0.03774181],"study_design_scores_gemma":[0.0002838584,0.00005150503,0.001916857,0.00001972243,0.0001882584,2.729038e-7,0.00003730685,0.962694,0.03139146,0.003270228,0.00007524547,0.00007129901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.165443,0.0000199093,0.8338196,0.0001162119,0.0002505053,0.0002060932,0.00002606263,0.00002710627,0.00009150324],"genre_scores_gemma":[0.9984139,0.00002737767,0.0012637,0.0002279765,0.000002268631,0.00002483227,0.000005860828,0.000002252684,0.00003178846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.832971,"threshold_uncertainty_score":0.3200155,"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."}}