Concepts2
📚TheoryIntermediate
Scaling Laws
Scaling laws say that model loss typically follows a power law that improves predictably as you increase parameters, data, or compute.
#scaling laws#power law#chinchilla scaling+12
📚TheoryIntermediate
Bias-Variance Tradeoff
The bias–variance tradeoff explains how prediction error splits into bias squared, variance, and irreducible noise for squared loss.
#bias variance tradeoff#mse decomposition#polynomial regression+12