First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces

by   Michael I. Jordan, et al.

From optimal transport to robust dimensionality reduction, a plethora of machine learning applications can be cast into the min-max optimization problems over Riemannian manifolds. Though many min-max algorithms have been analyzed in the Euclidean setting, it has proved elusive to translate these results to the Riemannian case. Zhang et al. [2022] have recently shown that geodesic convex concave Riemannian problems always admit saddle-point solutions. Inspired by this result, we study whether a performance gap between Riemannian and optimal Euclidean space convex-concave algorithms is necessary. We answer this question in the negative-we prove that the Riemannian corrected extragradient (RCEG) method achieves last-iterate convergence at a linear rate in the geodesically strongly-convex-concave case, matching the Euclidean result. Our results also extend to the stochastic or non-smooth case where RCEG and Riemanian gradient ascent descent (RGDA) achieve near-optimal convergence rates up to factors depending on curvature of the manifold.


page 1

page 2

page 3

page 4


Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

In this work, we study optimization problems of the form min_x max_y f(x...

Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds

Numerous applications in machine learning and data analytics can be form...

Accelerated Single-Call Methods for Constrained Min-Max Optimization

We study first-order methods for constrained min-max optimization. Exist...

On a class of geodesically convex optimization problems solved via Euclidean MM methods

We study geodesically convex (g-convex) problems that can be written as ...

Min-Max Optimization Made Simple: Approximating the Proximal Point Method via Contraction Maps

In this paper we present a first-order method that admits near-optimal c...

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent

We study first-order optimization algorithms for computing the barycente...

Generalization in Supervised Learning Through Riemannian Contraction

We prove that Riemannian contraction in a supervised learning setting im...

Please sign up or login with your details

Forgot password? Click here to reset