Learning Neural Random Fields with Inclusive Auxiliary Generators
share
In this paper we develop Neural Random Field learning with Inclusive-divergence minimized Auxiliary Generators (NRF-IAG), which is under-appreciated in the literature. The contributions are two-fold. First, we rigorously apply the stochastic approximation algorithm to solve the joint optimization and provide theoretical justification. The new approach of learning NRF-IAG achieves superior unsupervised learning performance competitive with state-of-the-art deep generative models (DGMs) in terms of sample generation quality. Second, semi-supervised learning (SSL) with NRF-IAG gives rise to strong classification results comparable to state-of-art DGM-based SSL methods, and simultaneously achieves superior generation. This is in contrast to the conflict of good classification and good generation, as observed in GAN-based SSL.
READ FULL TEXT
