Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
This work addresses the problem of efficient and unified probabilistic modeling for researchers in machine learning, offering a robust method that is incremental by building on existing techniques like variational and adversarial learning.
The paper tackles the challenge of jointly training generator, energy-based, and inference models by proposing the divergence triangle framework, which integrates multiple learning approaches and eliminates the need for costly MCMC methods, demonstrating capabilities in learning well-formed energy landscapes, direct sampling, and faithful reconstruction from incomplete data.
This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence in a unified probabilistic formulation. This unification makes the processes of sampling, inference, energy evaluation readily available without the need for costly Markov chain Monte Carlo methods. Our experiments demonstrate that the divergence triangle is capable of learning (1) an energy-based model with well-formed energy landscape, (2) direct sampling in the form of a generator network, and (3) feed-forward inference that faithfully reconstructs observed as well as synthesized data. The divergence triangle is a robust training method that can learn from incomplete data.