Generative Adversarial Networks (GANs) is a novel class of deep generative models that
has recently gained significant attention. GANs learn complex and high-dimensional …

We propose in this paper a novel approach to tackle the problem of mode collapse
encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be …

Generative adversarial networks (GANs) have recently attracted attention owing to their
impressive ability in generating high-quality and novel synthetic datasets such as signals …

We propose a new formulation for learning generative adversarial networks (GANs) using
optimal transport cost (the general form of Wasserstein distance) as the objective criterion to …

Abstract Generative Adversarial Networks (GANs) are a powerful class of deep generative
models. In this paper, we extend GAN to the problem of generating data that are not only …

Error disagreement-based active learning (AL) selects the data that maximally update the
error of a classification hypothesis. However, poor human supervision (eg, few labels …

One of the challenging problems in sequence generation tasks is the optimized generation
of sequences with specific desired goals. Current sequential generative models mainly …

Generative adversarial networks (GAN) have been widely used in the field of image-to-
image translation. In this paper, we have proposed a novel object extraction and …

ML2R Coding Nuggets: Linear Programming Page 1 ML2R Coding Nuggets Solving Linear
Programming Problems Pascal Welke∗ Machine Learning Rhine-Ruhr University of Bonn Bonn …

In this paper we introduce a projected gradient descent algorithm to find kernel minimum
enclosing balls and compare it to a gradient based Frank-Wolfe algorithm. We base our …