A Mirror Descent Perspective on Classical and Quantum Blahut-Arimoto Algorithms

The Blahut-Arimoto algorithm is a well known method to compute classical channel capacities and rate-distortion functions. Recent works have extended this algorithm to compute various quantum analogs of these quantities. In this paper, we show how these Blahut-Arimoto algorithms are special instances of mirror descent, which is a well-studied generalization of gradient descent for constrained convex optimization. Using new convex analysis tools, we show how relative smoothness and strong convexity analysis recovers known sublinear and linear convergence rates for Blahut-Arimoto algorithms. This mirror descent viewpoint allows us to derive related algorithms with similar convergence guarantees to solve problems in information theory for which Blahut-Arimoto-type algorithms are not directly applicable. We apply this framework to compute energy-constrained classical and quantum channel capacities, classical and quantum rate-distortion functions, and approximations of the relative entropy of entanglement, all with provable convergence guarantees.