Statistics

Why does **Sample Covariance** have: $\frac{1}{n-1} \sum_{i=1}^n (x_i - \bar{x})^2$ but **Population Covariance** $\frac{1}{n} \sum_{i=1}^n (x_i - \bar{x})^2$

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 $L(W) = ||y - Wx||^2 + \lambda ||W||^2$

It's "M" for mini, should be "W" for "wumbo". - Patrick Star on Isomorphic Representations

Finding the Maximum Likelihood Estimation of Data with Gaussian Noise Equivalent to Linear Regression

Deriving Linear Regression Normal Form & Showing its Properties