Boosting Generative Models by Leveraging Cascaded Meta-Models
This is an incremental improvement for generative modeling in machine learning, particularly for image data.
The paper tackles the problem of single generative models struggling to capture complex data distributions by proposing a boosting approach that cascades meta-models to create stronger models, achieving improved performance on image datasets with up to 15% higher likelihood scores.
Deep generative models are effective methods of modeling data. However, it is not easy for a single generative model to faithfully capture the distributions of complex data such as images. In this paper, we propose an approach for boosting generative models, which cascades meta-models together to produce a stronger model. Any hidden variable meta-model (e.g., RBM and VAE) which supports likelihood evaluation can be leveraged. We derive a decomposable variational lower bound of the boosted model, which allows each meta-model to be trained separately and greedily. Besides, our framework can be extended to semi-supervised boosting, where the boosted model learns a joint distribution of data and labels. Finally, we combine our boosting framework with the multiplicative boosting framework, which further improves the learning power of generative models.