We show that the conditional gradient method for the convex composite problem \[\min_x\{f(x) + \Psi(x)\}\] generates primal and dual iterates with a duality gap converging to zero provided a suitable growth property holds and the algorithm makes a judicious choice of stepsizes. The rate of convergence of the duality gap to zero ranges from sublinear to linear depending on the degree of the growth property. The growth property and convergence results depend exclusively on the pair $(f,\Psi)$. They are both affine invariant and norm-independent.
Citation
Working Paper. Carnegie Mellon University. December, 2021.