Christian Kroer

First-Order Methods with Increasing Iterate Averaging for Solving Saddle-Point Problems

2019 · arXiv (Cornell University)

First-order methods are known to be among the fastest algorithms for solving large-scale convex-concave saddle-point problems. Algorithms that achieve a theoretical convergence rate on the order of $1/T$ are known, but these often rely on …

Increasing Iterate Averaging for Solving Saddle-Point Problems

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Many problems in machine learning and game theory can be formulated as saddle-point problems, for which various first-order methods have been developed and proven efficient in practice. Under the general convex-concave assumption, most first-order methods …