This arXiv entry presents a book on the mathematical foundations of data science. Its 16 chapters cover high-dimensional phenomena, singular value decomposition and PCA, linear regression and regularization, graphs and clustering, diffusion maps, random projections, optimization, classification, an introduction to deep learning, graph Laplacian limits, concentration of measure, matrix concentration inequalities, compressed sensing, sparsity, and low-rank matrix recovery. The supplied abstract does not include author information, page count, prerequisites, or experimental evaluations.
No heat snapshots are available in the last 24 hours.