Implementation and survey of similarity search methods that rely on dimensionality reduction (e.g. LSH), D-dimensional vector clustering

approximation algorithms for exact nearest neighbors search and clustering on multi-dimensional vectors

Evaluating several new approaches to improve convergence of Randomized Kaczmarz (RK) for consistent ill-conditioned systems. This project explores the availability of convergence information among pairwise row differences and analyzes sampling techniques that involve clustering and spectral analysis.