On the Benefit of Width for Neural Networks: Disappearance of Basins (Q5097010): Difference between revisions

@@ Property / cites work @@
+Symmetry \& critical points for a model shallow neural network
+Normal rank
@@ Property / cites work @@
+Reconciling modern machine-learning practice and the classical bias–variance trade-off
+Normal rank
@@ Property / cites work @@
+Global Minima of Overparameterized Neural Networks
+Normal rank
@@ Property / cites work @@
+Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
+Normal rank
@@ Property / cites work @@
+Approximation by entire functions
@@ Property / cites work: Approximation by entire functions / rank @@
+Normal rank
@@ Property / cites work @@
+Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
+Normal rank
@@ Property / cites work @@
+The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
+Normal rank
@@ Property / cites work @@
+A mean field view of the landscape of two-layer neural networks
+Normal rank
@@ Property / cites work @@
+Mean Field Analysis of Deep Neural Networks
@@ Property / cites work: Mean Field Analysis of Deep Neural Networks / rank @@
+Normal rank
@@ Property / cites work @@
+Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
+Normal rank
@@ Property / cites work @@
+Spurious Valleys in Two-layer Neural Network Optimization Landscapes
+Normal rank
@@ Property / cites work @@
+Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
+Normal rank
@@ Property / cites work @@
+Gradient descent optimizes over-parameterized deep ReLU networks
+Normal rank