In this paper we present a variant of random coordinate descent method for solving linearly constrained convex optimization problems with composite objective function. If the smooth part has Lipschitz continuous gradient, then the method terminates with an ϵ-optimal solution in O(N2/ϵ) iterations, where N is the number of blocks. For the class of problems with cheap coordinate derivatives we show that the new method is faster than methods based on full-gradient information. Analysis for rate of convergence in probability is also provided. For strongly convex functions our method converges linearly.
Citation
Technical Report, University Politehnica Bucharest, Spl. Independentei 313, pp. 1-20, June, 2012.