Poster
A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models
Maxim Kuznetsov · Daniil Polykovskiy · Dmitry Vetrov · Alex Zhebrak

Tue Dec 10th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #119

Generative models produce realistic objects in many domains, including text, image, video, and audio synthesis. Most popular models—Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs)—usually employ a standard Gaussian distribution as a prior. Previous works show that the richer family of prior distributions may help to avoid the mode collapse problem in GANs and to improve the evidence lower bound in VAEs. We propose a new family of prior distributions—Tensor Ring Induced Prior (TRIP)—that packs an exponential number of Gaussians into a high-dimensional lattice with a relatively small number of parameters. We show that these priors improve Fréchet Inception Distance for GANs and Evidence Lower Bound for VAEs. We also study generative models with TRIP in the conditional generation setup with missing conditions. Altogether, we propose a novel plug-and-play framework for generative models that can be utilized in any GAN and VAE-like architectures.

Author Information

Maxim Kuznetsov (Insilico Medicine)
Daniil Polykovskiy (Insilico Medicine)
Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)
Alex Zhebrak (Insilico Medicine)

More from the Same Authors