Conjugate Energy-Based Models
This work addresses the need for more flexible similarity measures in unsupervised learning for researchers and practitioners in machine learning, though it appears incremental as it builds upon existing energy-based models and variational autoencoders.
The authors tackled the problem of unsupervised learning of flexible data representations by proposing conjugate energy-based models (CEBMs), which define a joint density over data and latent variables without a generator network, achieving competitive results in image modeling, latent space predictive power, and out-of-domain detection on various datasets.
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over data and a tractable posterior over latent variables. CEBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping from data to latent variables. However, these models omit a generator network, which allows them to learn more flexible notions of similarity between data points. Our experiments demonstrate that conjugate EBMs achieve competitive results in terms of image modelling, predictive power of latent space, and out-of-domain detection on a variety of datasets.