Pages that link to "Item:Q2039801"

The following pages link to Linearized two-layers neural networks in high dimension (Q2039801):

Displaying 18 items.

• Linear neural networks revisited: from PageRank to family happiness (Q1979855) (← links)
• The interpolation phase transition in neural networks: memorization and generalization under lazy training (Q2105197) (← links)
• Surprises in high-dimensional ridgeless least squares interpolation (Q2131262) (← links)
• Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration (Q2134105) (← links)
• A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics (Q2197845) (← links)
• Landscape and training regimes in deep learning (Q2231925) (← links)
• A priori estimates of the population risk for two-layer neural networks (Q2282333) (← links)
• The Study of Architecture MLP with Linear Neurons in Order to Eliminate the “vanishing Gradient” Problem (Q5077554) (← links)
• Overparameterization and Generalization Error: Weighted Trigonometric Interpolation (Q5088865) (← links)
• Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective (Q5131154) (← links)
• (Q5159408) (← links)
• (Q5159429) (← links)
• Wide neural networks of any depth evolve as linear models under gradient descent ^* (Q5857449) (← links)
• Deep learning: a statistical viewpoint (Q5887827) (← links)
• Neural network approximation (Q5887830) (← links)
• Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits (Q6044638) (← links)
• Weighted neural tangent kernel: a generalized and improved network-induced kernel (Q6134348) (← links)
• Precise learning curves and higher-order scaling limits for dot-product kernel regression (Q6611439) (← links)