Pages that link to "Item:Q1650102"

The following pages link to A random matrix approach to neural networks (Q1650102):

Displaying 13 items.

• Eigenvalue distribution of some nonlinear models of random matrices (Q2076620) (← links)
• A note on the Pennington-Worah distribution (Q2332995) (← links)
• Free dynamics of feature learning processes (Q2679634) (← links)
• Halting time is predictable for large models: a universality property and average-case analysis (Q2697399) (← links)
• A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent* (Q5020045) (← links)
• Generalisation error in learning with random features and the hidden manifold model* (Q5020057) (← links)
• On the empirical spectral distribution for certain models related to sample covariance matrices with different correlations (Q5092965) (← links)
• (Q5159429) (← links)
• Deep learning: a statistical viewpoint (Q5887827) (← links)
• Large-dimensional random matrix theory and its applications in deep learning and wireless communications (Q6063730) (← links)
• Designing universal causal deep learning models: The geometric (Hyper)transformer (Q6196301) (← links)
• The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression (Q6550964) (← links)
• Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks (Q6590448) (← links)