IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression

Understand

In this paper we analyse and improve integer discrete flows for lossless compression.

• Integer discrete flows are a recently proposed class of models that learn invertible transformations for integer-valued random variables.
• Their discrete nature makes them particularly suitable for lossless compression with entropy coding schemes.
• We start by investigating a recent theoretical claim that states that invertible flows for discrete random variables are less flexible than their continuous counterparts.