Pages that link to "Item:Q5856249"

The following pages link to Scaling description of generalization with number of parameters in deep learning (Q5856249):

Displaying 16 items.

• Normalization effects on shallow neural networks and related asymptotic expansions (Q2072629) (← links)
• A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks (Q2103975) (← links)
• Surprises in high-dimensional ridgeless least squares interpolation (Q2131262) (← links)
• Landscape and training regimes in deep learning (Q2231925) (← links)
• Free dynamics of feature learning processes (Q2679634) (← links)
• Geometric compression of invariant manifolds in neural networks (Q3382321) (← links)
• Triple descent and the two kinds of overfitting: where and why do they appear?* (Q5020037) (← links)
• An analytic theory of shallow networks dynamics for hinge loss classification* (Q5020044) (← links)
• The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima (Q5073270) (← links)
• Overparameterization and Generalization Error: Weighted Trigonometric Interpolation (Q5088865) (← links)
• (Q5159429) (← links)
• Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks (Q5885828) (← links)
• Large-dimensional random matrix theory and its applications in deep learning and wireless communications (Q6063730) (← links)
• High-Dimensional Analysis of Double Descent for Linear Regression with Random Projections (Q6151666) (← links)
• Harmonic analysis of network systems via kernels and their boundary realizations (Q6160662) (← links)
• Normalization effects on deep neural networks (Q6194477) (← links)