Autoregressive Models: What Are They Good For?

10/17/2019
by   Murtaza Dalal, et al.
37

Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density estimators in two settings – as a learning signal for image translation, and as an outlier detector – and find that these density estimates are much less reliable than previously thought. We examine the underlying optimization issues from both an empirical and theoretical perspective, and provide a toy example that illustrates the problem. Overwhelmingly, we find that density estimates do not correlate with perceptual quality and are unhelpful for downstream tasks.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset