Entropy-like proximal methods in convex programming

The authors study an extension of the proximal method for programming, where the quadratic regularization kernel is substituted by a class of convex statistical distances, called ℝrsquo;-divergences, which are typically entropy-like in form. After establishing several basic properties of these quasi-distances, they present a convergence analysis of the resulting entropy-like proximal algorithm. Applying this algorithm to the dual of a convex program, the authors recover a wide class of nonquadratic multiplier methods and prove their convergence.