On the Benefit of Width for Neural Networks: Disappearance of Basins
From MaRDI portal
Publication:5097010
DOI10.1137/21M1394205zbMath1493.68331arXiv1812.11039OpenAlexW4289334798MaRDI QIDQ5097010
Dawei Li, Tian Ding, Ruoyu Sun
Publication date: 19 August 2022
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.11039
Related Items
Cites Work
- Approximation by entire functions
- Symmetry \& critical points for a model shallow neural network
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
- Gradient descent optimizes over-parameterized deep ReLU networks
- Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
- A mean field view of the landscape of two-layer neural networks
- Global Minima of Overparameterized Neural Networks
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- Mean Field Analysis of Deep Neural Networks
- Spurious Valleys in Two-layer Neural Network Optimization Landscapes
- Reconciling modern machine-learning practice and the classical bias–variance trade-off
- Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
- Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
