The following pages link to Mikhail Belkin (Q703084):
Displaying 12 items.
- Semi-supervised learning on Riemannian manifolds (Q703086) (← links)
- Towards a theoretical foundation for Laplacian-based manifold methods (Q959898) (← links)
- Data spectroscopy: eigenspaces of convolution operators and clustering (Q1043719) (← links)
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networks (Q2134108) (← links)
- Consistency of spectral clustering (Q2426615) (← links)
- Heat flow and a faster algorithm to compute the surface area of a convex body (Q2868081) (← links)
- (Q2896059) (← links)
- (Q3174044) (← links)
- Overparameterized neural networks implement associative memory (Q5073192) (← links)
- Reconciling modern machine-learning practice and the classical bias–variance trade-off (Q5218544) (← links)
- On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions (Q6070298) (← links)
- A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors (Q6090836) (← links)
