Abstract: Flow-based generative models refer to deep generative models with
tractable likelihoods, and offer several attractive properties including
efficient density estimation and sampling. Despite many advantages,
current formulations (e.g., normalizing flow) often have an expensive memory/runtime footprint, which hinders their use in a number of applications.
In this paper, we consider the setting where we have access to an autoencoder, which is
suitably effective for the dataset of interest. Under some mild conditions,
we show that we can calculate a mapping to a RKHS which subsequently enables deploying
mature ideas from the kernel methods literature for flow-based generative models. Specifically, we can explicitly map the RKHS distribution (i.e.,
approximate the flow) to match or align with
a template/well-characterized distribution, via kernel transfer operators. This leads to a direct and resource efficient approximation avoiding iterative optimization. We empirically show that this simple idea yields competitive results on popular datasets such as CelebA,
as well as promising results on a public 3D brain imaging dataset where the sample sizes are much smaller.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
One-sentence Summary: (almost) training-free generative model
Supplementary Material: zip
Reviewed Version (pdf): https://openreview.net/references/pdf?id=JWHoA91DWb
12 Replies
Loading