MML-16-08: Generalization Theory: Empirical Risk Minimization, Bias-Variance Decomposition – Practice Quiz

Master the mathematical foundations of statistical learning and generalization: population vs. empirical risk minimization, optimism of training error, approximation-estimation excess risk decomposition, exact derivation of the Bias-Variance-Noise decomposition under squared loss, spectral variance blow-up at the interpolation threshold, and the modern Double Descent curve.