ESTIMATION OF VECTORS SIMILARITY BY THEIR RANDOMIZED BINARY PROJECTIONS

摘要

We analyze the estimation of the angle, scalar product, and the Euclidean distance of real-valued vectors using binary vectors with controlled sparsity. Transformation is carried out by projection using a binary random matrix with elements {0,1} and the output threshold transformation. We also provide a comparative analysis of the error obtained while estimating the similarity measures of input vectors by some similarity measures of output binary vectors based on their scalar product.