Limited-memory BFGS (L-BFGS; Liu and Nocedal,) is often considered to be the method of
choice for continuous optimization when first-or second-order information is available …

Despite the huge spread and economical importance of configurable software systems,
there is unsatisfactory support in utilizing the full potential of these systems with respect to …

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 …

For hydrodynamic optimization using computational fluid dynamics methods, the high
computational cost impedes the use of evolutionary algorithms since they require evaluation …

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

Generative adversarial networks (GANs) exhibit training pathologies that can lead to
convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary …

Generative Adversarial Networks (GANs) are popular tools for generative modeling. The
dynamics of their adversarial learning give rise to convergence pathologies during training …

The covariance matrix adaptation evolution strategy (CMA-ES) is a competitive evolutionary
algorithm (EA) for difficult continuous optimization problems. However, expensive function …

A number of surrogate-assisted evolutionary algorithms are being developed for tackling
expensive multiobjective optimization problems. On the one hand, a relatively broad range …

Decomposition-based evolutionary algorithms have been applied with success to multi-
objective optimization problems where they are broken into several subproblems, and …