Benign overfitting in linear regression (Q5073215): Difference between revisions

@@ Property / cites work @@
+The elements of statistical learning. Data mining, inference, and prediction
+Normal rank
@@ Property / cites work @@
+The Hilbert kernel regression estimate.
@@ Property / cites work: The Hilbert kernel regression estimate. / rank @@
+Normal rank
@@ Property / cites work @@
+Just interpolate: kernel ``ridgeless'' regression can generalize
+Normal rank
@@ Property / cites work @@
+Reconciling modern machine-learning practice and the classical bias–variance trade-off
+Normal rank
@@ Property / cites work @@
+Two Models of Double Descent for Weak Features
@@ Property / cites work: Two Models of Double Descent for Weak Features / rank @@
+Normal rank
@@ Property / cites work @@
+Surprises in high-dimensional ridgeless least squares interpolation
+Normal rank
@@ Property / cites work @@
+A Note on Pseudoinverses
@@ Property / cites work: A Note on Pseudoinverses / rank @@
+Normal rank
@@ Property / cites work @@
+Gradient descent optimizes over-parameterized deep ReLU networks
+Normal rank
@@ Property / cites work @@
+Efficient agnostic learning of neural networks with bounded fan-in
+Normal rank
@@ Property / cites work @@
+Breaking the Curse of Dimensionality with Convex Neural Networks
+Normal rank
@@ Property / cites work @@
+The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
+Normal rank
@@ Property / cites work @@
+.1162/153244303321897690
@@ Property / cites work: 10.1162/153244303321897690 / rank @@
+Normal rank
@@ Property / cites work @@
+Size-independent sample complexity of neural networks
+Normal rank