MML-14-12: PCA via Covariance Eigendecomposition vs. SVD: Computational Tradeoffs – Practice Quiz

35 worked single-select and multiselect questions on PCA via Covariance Eigendecomposition vs. SVD: Computational Tradeoffs. Cognitive level: Tier 2–3. Prerequisites: QS 14.11, Part 05.

Learning objectives: Relate PCA covariance eigenpairs to data singular triplets; Compute scores, variances and residual energy with consistent normalization; Choose feature-space or sample-space methods by shape and memory; Diagnose conditioning and floating-point spectral artifacts; Explain truncated, randomized and incremental solvers; Handle sparse centering, whitening and validation-fold preprocessing.

Each item is self-contained, with calculations, model diagnostics and explanations of every distractor. Study references: Mathematics for Machine Learning; scikit-learn decomposition guide.