Jun 4, 2022 · Inspired by this result, we study whether a performance gap between Riemannian and optimal Euclidean space convex-concave algorithms is ...

Our work is the first to answer the question in the negative:We prove that the Riemannian corrected extragradient (RCEG) method achieves last-iterate at ...

Inspired by this result, we study whether a performance gap between Riemannian and optimal Euclidean space convex-concave algorithms is necessary. We answer ...

Oct 31, 2022 · The paper analyzes the performance of a few of the recent algorithms for min-max optimization over manifolds. The analysis is extensive and is ...

First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces ... Sion's Manifold Min-Max Theorem. If a bifunction f : M×N → R is geodesically. ( ...

Sep 28, 2022 · Inspired by this result, we study whether a performance gap between Riemannian and optimal Euclidean space convex-concave algorithms is ...

Jun 7, 2022 · Though many min-max algorithms have been analyzed in the Euclidean setting, it has proved elusive to translate these results to the Riemannian ...

Explicit second-order min-max optimization methods with optimal convergence guarantee ... First-order algorithms for min-max optimization in geodesic metric ...

The second main result is a specialization to geodesically complete Riemannian manifolds: here, we devise and analyze the complexity of first-order methods for ...

We take a step towards understanding certain nonconvex-nonconcave minimax problems that do remain tractable. Specifically, we study minimax problems cast in ...