Exact Worst-Case Performance of First-Order Methods for Composite Convex Optimization

We provide a framework for computing the exact worst-case performance of any algorithm belonging to a broad class of oracle-based first-order methods for composite convex optimization, including those performing explicit, projected, proximal, conditional and inexact (sub)gradient steps. We simultaneously obtain tight worst-case convergence guarantees and explicit problems on which the algorithm reaches this worst-case. We achieve this by reducing the computation of the worst-case to solving a convex semidefinite program, generalizing previous works on performance estimation by Drori and Teboulle [13] and the authors [38]. We use these developments to obtain a tighter analysis of the proximal point algorithm, several variants of fast proximal gradient, conditional gradient, subgradient and alternating projection methods. In particular, we present a new analytical guarantee for the proximal point algorithm that is twice better than previously known, and improve the standard convergence guarantee for the conditional gradient method by more than a factor of two. We also show how the optimized gradient method proposed by Kim and Fessler in [20] can be extended by incorporating a projection or a proximal operator, which leads to an algorithm that converges in the worst-case twice as fast as the standard accelerated proximal gradient method [3].