AABI

We propose conjugate energy-based models (EBMs), a class of deep latent-variable models with a tractable posterior. Conjugate EBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping between data …

We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an inclusive or exclusive KL divergence at each level of nesting. NVI is applicable to many commonly-used importance …