A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions (Q2145074): Difference between revisions

@@ Property / DOI @@
-.1016/j.jco.2022.101646
@@ Property / DOI: 10.1016/j.jco.2022.101646 / rank @@
-Normal rank
@@ Property / OpenAlex ID @@
+W3132264265
@@ Property / OpenAlex ID: W3132264265 / rank @@
+Normal rank
@@ Property / Wikidata QID @@
+Q113871711
@@ Property / Wikidata QID: Q113871711 / rank @@
+Normal rank
@@ Property / arXiv ID @@
+.09924
@@ Property / arXiv ID: 2102.09924 / rank @@
+Normal rank
@@ Property / cites work @@
+Breaking the Curse of Dimensionality with Convex Neural Networks
+Normal rank
@@ Property / cites work @@
+Full error analysis for the training of deep neural networks
+Normal rank
@@ Property / cites work @@
+Non-convergence of stochastic gradient descent in the training of deep neural networks
+Normal rank
@@ Property / cites work @@
+A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
+Normal rank
@@ Property / cites work @@
+Q4969246
@@ Property / cites work: Q4969246 / rank @@
+Normal rank
@@ Property / cites work @@
+Strong error analysis for stochastic gradient descent optimization algorithms
+Normal rank
@@ Property / cites work @@
+Lower error bounds for the stochastic gradient descent optimization algorithm: sharp convergence rates for slowly and fast decaying learning rates
+Normal rank
@@ Property / cites work @@
+Dying ReLU and Initialization: Theory and Numerical Examples
+Normal rank
@@ Property / cites work @@
+Q3996430
@@ Property / cites work: Q3996430 / rank @@
+Normal rank
@@ Property / cites work @@
+Gradient descent optimizes over-parameterized deep ReLU networks
+Normal rank
@@ Property / DOI @@
+.1016/J.JCO.2022.101646
@@ Property / DOI: 10.1016/J.JCO.2022.101646 / rank @@
+Normal rank