Goto

Collaborating Authors

 bimdsm



Table A: FID on CIFAR10. means averaged by 5 runs. Methods with use comparable networks. Method FID FID-ES Flow-CE [ 1*] 37.30 - V AE-EBL VM[2*] 30.1 - MDSM [34] - 31.7 MDSM

Neural Information Processing Systems

We thank all reviewers for their valuable comments. Below, we first address the common concerns and then answer the detailed questions. It leads to smaller bias (see Fig. A), which also agrees with Thm. 2. First, introducing latent variables can improve the sample quality (w.r.t. Indeed, we update Tab. 2 and obtain Tab. As stated in L290, a similar protocol is adopted in MDSM [34].