Binary Embedding: Fundamental Limits and Fast Algorithm

Abstract: Binary embedding is a nonlinear dimension reduction methodology where high dimensional data are embedded into the Hamming cube while preserving the structure of the original space. Specifically, for an arbitrary $N$ distinct points in $\mathbb{S}<sup>{p-1}$, our goal is to encode each point using $m$-dimensional binary strings such that we can reconstruct their geodesic distance up to $\delta$ uniform distortion. Existing binary embedding algorithms either lack theoretical guarantees or suffer from running time $O\big(mp\big)$. We make three contributions: (1) we establish a lower bound that shows any binary embedding oblivious to the set of points requires $m = \Omega(\frac{1}{\delta<sup>2}\log{N})$ bits and a similar lower bound for non-oblivious embeddings into Hamming distance; (2) [DELETED, see comment]; (3) we also provide an analytic result about embedding a general set of points $K \subseteq \mathbb{S}<sup>{p-1}$ with even infinite size. Our theoretical findings are supported through experiments on both synthetic and real data sets.