Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
This incremental method addresses bias correction for users of generative models in applications like classification and reinforcement learning.
The paper tackles bias in learned generative models by applying likelihood-free importance weighting, which consistently improves sample quality metrics and demonstrates utility in data augmentation and model-based policy evaluation.
A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions. When the likelihood ratio is unknown, it can be estimated by training a probabilistic classifier to distinguish samples from the two distributions. We employ this likelihood-free importance weighting method to correct for the bias in generative models. We find that this technique consistently improves standard goodness-of-fit metrics for evaluating the sample quality of state-of-the-art deep generative models, suggesting reduced bias. Finally, we demonstrate its utility on representative applications in a) data augmentation for classification using generative adversarial networks, and b) model-based policy evaluation using off-policy data.