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

by   Yang Cai, et al.

Numerous applications in machine learning and data analytics can be formulated as equilibrium computation over Riemannian manifolds. Despite the extensive investigation of their Euclidean counterparts, the performance of Riemannian gradient-based algorithms remain opaque and poorly understood. We revisit the original scheme of Riemannian gradient descent (RGD) and analyze it under a geodesic monotonicity assumption, which includes the well-studied geodesically convex-concave min-max optimization problem as a special case. Our main contribution is to show that, despite the phenomenon of distance distortion, the RGD scheme, with a step size that is agnostic to the manifold's curvature, achieves a curvature-independent and linear last-iterate convergence rate in the geodesically strongly monotone setting. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence in the Riemannian setting has not been considered before.


page 1

page 2

page 3

page 4


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

From optimal transport to robust dimensionality reduction, a plethora of...

On The Convergence of Gradient Descent for Finding the Riemannian Center of Mass

We study the problem of finding the global Riemannian center of mass of ...

R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate

We study smooth stochastic optimization problems on Riemannian manifolds...

Convergence analysis of subdivision processes on the sphere

This paper provides a strategy to analyse the convergence of nonlinear a...

Curvature-Dependant Global Convergence Rates for Optimization on Manifolds of Bounded Geometry

We give curvature-dependant convergence rates for the optimization of we...

Minimizing Dynamic Regret on Geodesic Metric Spaces

In this paper, we consider the sequential decision problem where the goa...

Numerical Accuracy of Ladder Schemes for Parallel Transport on Manifolds

Parallel transport is a fundamental tool to perform statistics on Rie-ma...

Please sign up or login with your details

Forgot password? Click here to reset