Chris Chu

On the Convergence of Randomized Bregman Coordinate Descent for Non-Lipschitz Composite Problems

We propose a new randomized Bregman (block) coordinate descent (RBCD) method for minimizing a composite problem, where the objective function could be either convex or nonconvex, and the smooth part are freed from the global Lipschitz-continuous (partial) gradient assumption. Under the notion of rel…