Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric J. Horvitz, Stefano Ermon

Aug-20-2025, 04:33:22 GMT–Neural Information Processing Systems 

A learned generative model often produces biased statistics relative to the underlying data distribution.