Contributed Talk
in
Workshop: Neural Compression: From Information Theory to Applications

Spotlight 6: Lucas Theis|Jonathan Ho, Importance weighted compression

[ Abstract ] [ Project Page ]
Fri 7 May 11:30 a.m. PDT — 11:35 a.m. PDT

Abstract:

The connection between variational autoencoders (VAEs) and compression is well established and they have been used for both lossless and lossy compression. Compared to VAEs, importance-weighted autoencoders (IWAEs) achieve a larger bound on the log-likelihood. However, it is not well understood whether a similar connection between IWAEs and compression exists and whether the improved loss corresponds to better compression performance. Here we show that the loss of IWAEs can indeed be interpreted as the cost of lossless or lossy compression schemes, and using IWAEs for compression can lead to small improvements in performance.