Two Models of Double Descent for Weak Features (Q5027013): Difference between revisions

@@ Property / arXiv ID @@
+.07571
@@ Property / arXiv ID: 1903.07571 / rank @@
+Normal rank
@@ Property / cites work @@
+Concentration inequalities for sampling without replacement
+Normal rank
@@ Property / cites work @@
+Benign overfitting in linear regression
@@ Property / cites work: Benign overfitting in linear regression / rank @@
+Normal rank
@@ Property / cites work @@
+Reconciling modern machine-learning practice and the classical bias–variance trade-off
+Normal rank
@@ Property / cites work @@
+Dynamics of batch training in a perceptron
@@ Property / cites work: Dynamics of batch training in a perceptron / rank @@
+Normal rank
@@ Property / cites work @@
+How Many Variables Should be Entered in a Regression Equation?
+Normal rank
@@ Property / cites work @@
+An elementary proof of a theorem of Johnson and Lindenstrauss
+Normal rank
@@ Property / cites work @@
+Limiting empirical singular value distribution of restrictions of discrete Fourier transform matrices
+Normal rank
@@ Property / cites work @@
+Generalization in a linear perceptron in the presence of noise
+Normal rank
@@ Property / cites work @@
+Smallest singular value of a random rectangular matrix
+Normal rank
@@ Property / cites work @@
+A jamming transition from under- to over-parametrization affects generalization in deep learning
+Normal rank
@@ Property / cites work @@
+High-Dimensional Probability
@@ Property / cites work: High-Dimensional Probability / rank @@
+Normal rank
@@ Property / OpenAlex ID @@
+W3111350549
@@ Property / OpenAlex ID: W3111350549 / rank @@
+Normal rank