Self-Adversarially Learned Bayesian Sampling
This addresses inefficiencies in Bayesian sampling for unsupervised deep learning, though it appears incremental as it builds on existing methods like SG-MCMC and SVGD.
The paper tackles the problem of highly correlated and inefficient sample generation in scalable Bayesian sampling by proposing a self-adversarial learning framework that learns a conditional generator to mimic Markov kernels, resulting in improved sampling efficiency and sample quality as verified in experiments.
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD), the generated samples are typically highly correlated. Moreover, their sample-generation processes are often criticized to be inefficient. In this paper, we propose a novel self-adversarial learning framework that automatically learns a conditional generator to mimic the behavior of a Markov kernel (transition kernel). High-quality samples can be efficiently generated by direct forward passes though a learned generator. Most importantly, the learning process adopts a self-learning paradigm, requiring no information on existing Markov kernels, e.g., knowledge of how to draw samples from them. Specifically, our framework learns to use current samples, either from the generator or pre-provided training data, to update the generator such that the generated samples progressively approach a target distribution, thus it is called self-learning. Experiments on both synthetic and real datasets verify advantages of our framework, outperforming related methods in terms of both sampling efficiency and sample quality.