Importance Weighted Generative Networks

2018/06/07 by Diesendruck, Maurice, Elenberg, Ethan R., Sen, Rajat +3
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1806.02512

Abstract

Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject to sample selection bias, or may be from a different but related distribution. We present methods based on importance weighting that can estimate the loss with respect to a target distribution, even if we cannot access that distribution directly, in a variety of settings. These estimators, which differentially weight the contribution of data to the loss function, offer both theoretical guarantees and impressive empirical performance.

Related

• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Efficient Weighted Sampling via Score-based Generative Models
• Compressive Learning of Generative Networks
• A Universal Marginalizer for Amortized Inference in Generative Models
• Importance Weighted Autoencoders