Sharp Convergence Rates for Matching Pursuit

Abstract

We study the fundamental limits of matching pursuit, or the pure greedy algorithm, for approximating a target function f by a linear combination $f_{n}$ of n elements from a dictionary. When the target function is contained in the variation space corresponding to the dictionary, many impressive works over the past few decades have obtained upper and lower bounds on the error $\|f-f_{n}\|$ of matching pursuit, but they do not match. The main contribution of this paper is to close this gap and obtain a sharp characterization of the decay rate, $n^{-\alpha }$ , of matching pursuit. Specifically, we construct a worst-case dictionary which shows that the best-known upper bound cannot be substantially improved. It turns out that, unlike other greedy algorithm variants which converge at the optimal rate of $ n^{-1/2}$ , the convergence rate of $n^{-\alpha }$ is suboptimal. Here, $\alpha \approx 0.182$ is determined by the solution to a certain non-linear equation.