A One-bit, Comparison-Based Gradient Estimator

We study zeroth-order optimization for convex functions where we further assume that function evaluations are unavailable. Instead, one only has access to a , which given two points and returns a single bit of information indicating which point has larger function value, or . By treating the gradient as an unknown signal to be recovered, we show how one can use tools from one-bit compressed sensing to construct a robust and reliable estimator of the normalized gradient. We then propose an algorithm, coined SCOBO, that uses this estimator within a gradient descent scheme. We show that when has some low dimensional structure that can be exploited, SCOBO outperforms the state-of-the-art in terms of query complexity. Our theoretical claims are verified by extensive numerical experiments.
View on arXiv