LGMLNov 7, 2016

Unrolled Generative Adversarial Networks

arXiv:1611.02163v41069 citations
Originality Highly original
AI Analysis

This addresses a key challenge in training GANs for researchers and practitioners, offering a method to improve stability and performance in generative modeling.

The paper tackled the instability and mode collapse problems in Generative Adversarial Networks (GANs) by introducing an unrolled optimization method for the discriminator in the generator's objective, resulting in stabilized training, increased diversity, and better coverage of the data distribution.

We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.

Code Implementations9 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes