Generalization

Dataset normalization & uses including: LayerNorm, Dynamic Tanh, BatchNorm, RMSNorm, L1, & L2

L1 Lasso vs L2 Ridge Constraint's Effect on Weight Minimization

$L(w) = ||y-Xw||^2 + \lambda ||w||_1$ L1 Lasso Regularization & Weight Sparsity

How $\lambda$ affect the Bias & Variance for Ridge Regression?

What happens when we increase $\lambda$ in $L(W) = ||y - Wx||^2 + \lambda ||W||^2$

Connecting the Ubiquitous Ridge Regression $L(W) = ||Wx-b||^2 + \lambda ||W||^2$ to its Lagrange Multiplier Formulation

Informative Properties of the Ubiquitous L2 Squared Loss

Bias Variance Decomposition of Squared Loss

What's the Maximum Number of Points a Model can Classify? Understanding VC Dimension via Pascal’s Triangle

Feasibility of Learning via Hoeffding's Inequality