← Keywords

double descent

52 papers

Explore in graph

Co-occurring keywords

generalization error (285) neural network (6616) random feature (89) neural network optimization (1293) ensemble learning (1271) ridge regression (134) high-dimensional regression (142) linear regression (281) kernel methods (1096) random matrix theory (63)

Papers

Are All Linear Regions Created Equal? AISTATS 2022
Risk Monotonicity in Statistical Learning NIPS 2021
Kernel regression in high dimensions: Refined analysis beyond double descent AISTATS 2021
Taxonomizing local versus global structure in neural network loss landscapes NIPS 2021
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models ICML 2021
Asymptotics of Ridge Regression in Convolutional Models ICML 2021
Multiple Descent: Design Your Own Generalization Curve NIPS 2021
Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NIPS 2021
On the Role of Optimization in Double Descent: A Least Squares Study NIPS 2021
Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs IJCAI 2021
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021
The curious case of adversarially robust models: More data can help, double descend, or hurt generalization UAI 2021
Finite Versus Infinite Neural Networks: an Empirical Study NIPS 2020
Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime ICML 2020
Exact expressions for double descent and implicit regularization via surrogate random design NIPS 2020
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree NIPS 2020
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization ICML 2020
Generalisation error in learning with random features and the hidden manifold model ICML 2020
Generalization Error of Generalized Linear Models in High Dimensions ICML 2020
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors ICML 2020
Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model NIPS 2020
Triple descent and the two kinds of overfitting: where & why do they appear? NIPS 2020
Do We Need Zero Training Loss After Achieving Zero Training Error? ICML 2020
On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression NIPS 2020
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition NIPS 2020