AdaGAN: Boosting Generative Models

TL;DR

AdaGAN introduces an iterative boosting approach for generative models, combining multiple GAN components to improve training stability and address mode collapse, with proven convergence guarantees and experimental validation.

Contribution

It proposes AdaGAN, a novel boosting-based method that incrementally builds a mixture of GANs, enhancing diversity and convergence in generative modeling.

Findings

Addresses mode collapse in GANs.

Proves convergence of the boosting procedure.

Demonstrates improved sample diversity experimentally.

Abstract

Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to train and can suffer from the problem of missing modes where the model is not able to produce examples in certain regions of the space. We propose an iterative procedure, called AdaGAN, where at every step we add a new component into a mixture model by running a GAN algorithm on a reweighted sample. This is inspired by boosting algorithms, where many potentially weak individual predictors are greedily aggregated to form a strong composite predictor. We prove that such an incremental procedure leads to convergence to the true distribution in a finite number of steps if each step is optimal, and convergence at an exponential rate otherwise. We also illustrate experimentally that this procedure addresses the problem of missing modes.