Such output distributions are typically assumed to be fully-factorized.

However, it remains largely open to learn energy-based latent variable models (EBLVMs), exceptsomespecialcases. Thispaperpresents abi-levelscorematching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bilevel optimization problem. The higher level introduces a variational posterior of the latent variables and optimizes a modified SM objective, and the lower level optimizes the variational posterior to fit the true posterior.

Recently, there has been significant interest in utilizing this information in the context of deep neural networks; however,relatively little isknown about the quality ofexisting approximationsinthiscontext.

Recently, there has been significant interest in utilizing this information in the context of deep neural networks; however,relatively little isknown about the quality ofexisting approximationsinthiscontext.