Affine Invariant Convergence Rates of the Conditional Gradient Method
研究了凸复合问题中条件梯度法的收敛性,在适当增长性质下,对偶间隙收敛到零,速率从次线性到线性,且结果具有仿射不变性。
We show that the conditional gradient method for the convex composite problem 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 on the pair in an affine invariant and norm-independent fashion.