[edit]
Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2305-2313, 2021.
Abstract
We present a direct (primal only) derivation of Mirror Descent as a “partial” discretization of gradient flow on a Riemannian manifold where the metric tensor is the Hessian of the Mirror Descent potential function. We contrast this discretization to Natural Gradient Descent, which is obtained by a “full” forward Euler discretization. This view helps shed light on the relationship between the methods and allows generalizing Mirror Descent to any Riemannian geometry in Rd, even when the metric tensor is not a Hessian, and thus there is no “dual.”