In this paper, we study the problem of constrained min-max optimization in a black-box
setting, where the desired optimizer cannot access the gradients of the objective function but …

This paper proposes Friedrichs learning as a novel deep learning methodology that can
learn the weak solutions of PDEs via a minimax formulation, which transforms the PDE …

Co-evolutionary algorithms have a wide range of applications, such as in hardware design,
evolution of strategies for board games, and patching software bugs. However, these …

In this paper, we study zeroth-order algorithms for minimax optimization problems that are
nonconvex in one variable and strongly-concave in the other variable. Such minimax …

Generative Adversarial Networks (GANs) are difficult to train because of pathologies such as
mode and discriminator collapse. Similar pathologies have been studied and addressed in …

We propose an approach to saddle point optimization relying only on oracles that solve
minimization problems approximately. We analyze its convergence property on a strongly …

In this paper, we study zeroth-order algorithms for minimax optimization problems that are
nonconvex in one variable and strongly-concave in the other variable. Such minimax …

Abstract We investigate training Generative Adversarial Networks, GANs, with less data.
Subsets of the training dataset can express empirical sample diversity while reducing …

Nonconvex minimax problems have attracted significant interest in machine learning and
many other fields in recent years. In this paper, we propose a new zeroth-order alternating …

GANs are difficult to train due to convergence pathologies such as mode and discriminator
collapse. We introduce Lipizzaner, an open source software system that allows machine …