Pages that link to "Item:Q5872795"
From MaRDI portal
The following pages link to A jamming transition from under- to over-parametrization affects generalization in deep learning (Q5872795):
Displaying 21 items.
- Surprises in high-dimensional ridgeless least squares interpolation (Q2131262) (← links)
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networks (Q2134108) (← links)
- Landscape and training regimes in deep learning (Q2231925) (← links)
- On the stability and generalization of neural networks with VC dimension and fuzzy feature encoders (Q2235467) (← links)
- A statistician teaches deep learning (Q2241468) (← 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)
- Generalisation error in learning with random features and the hidden manifold model* (Q5020057) (← links)
- Two Models of Double Descent for Weak Features (Q5027013) (← links)
- Learning curves of generic features maps for realistic datasets with a teacher-student model* (Q5055409) (← links)
- Gradient descent dynamics and the jamming transition in infinite dimensions (Q5057865) (← links)
- (Q5148955) (← links)
- Scaling description of generalization with number of parameters in deep learning (Q5856249) (← links)
- Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks (Q5885828) (← links)
- Deep learning: a statistical viewpoint (Q5887827) (← links)
- Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation (Q5887828) (← links)
- The common intuition to transfer learning can win or lose: case studies for linear regression (Q6583519) (← links)
- Tradeoff of generalization error in unsupervised learning (Q6607283) (← links)
- Fluctuations, bias, variance and ensemble of learners: exact asymptotics for convex losses in high-dimension (Q6611433) (← links)
- Redundant representations help generalization in wide neural networks (Q6611451) (← links)
- Tuning parameters of deep neural network training algorithms pays off: a computational study (Q6635854) (← links)
