Gradient Estimators for Implicit Models
This addresses a bottleneck in training implicit models like GANs and simulators, offering a more stable method for researchers and practitioners, though it is incremental as it builds on existing gradient estimation techniques.
The paper tackles the problem of learning implicit models, which lack point-wise probability evaluation, by proposing the Stein gradient estimator to directly estimate the score function, eliminating the need for approximations that cause inaccurate updates. The result is demonstrated through improved sample diversity in entropy regularised GANs and applications in meta-learning for approximate inference.
Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objective for gradient-based optimisation, which is liable to produce inaccurate updates and thus poor models. This paper alleviates the need for such approximations by proposing the Stein gradient estimator, which directly estimates the score function of the implicitly defined distribution. The efficacy of the proposed estimator is empirically demonstrated by examples that include meta-learning for approximate inference, and entropy regularised GANs that provide improved sample diversity.