Relatively Smooth Convex Optimization by First-Order Methods, and Applications I: The Primal Gradient Scheme Attains f(x^k) − f(x) ≤ μD_h(x,x⁰)/((1+μ/(L−μ))^k − 1) ≤ (L−μ)D_h(x,x⁰)/kResearch Paper
Gradient methods for convex minimisation are usually analysed under two assumptions on the objective : its gradient is Lipschitz continuous (-smoothness), and, for linear rates, is strongly convex. Many objectives met in practice satisfy neither on their whole domain. The D-optimal design objective , the univariate…