Skip to content
conftrace_

wide neural network

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gradient descent (3) neural tangent kernel (2) neural network (1) linearized network (1) balancedness condition (1) bounded conditioning (1) regularity (1) sample points (1) sobolev loss (1) smoothing spline (1)

Papers

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse ICLR 2025 Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss ICML 2024 Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach ICLR 2024 Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks JMLR 2023 Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models ICLR 2022