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

by   Rianne van den Berg, et al.

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. Due to its discrete nature, they can be combined in a straightforward manner with entropy coding schemes for lossless compression without the need for bits-back coding. We discuss the potential difference in flexibility between invertible flows for discrete random variables and flows for continuous random variables and show that (integer) discrete flows are more flexible than previously claimed. We furthermore investigate the influence of quantization operators on optimization and gradient bias in integer discrete flows. Finally, we introduce modifications to the architecture to improve the performance of this model class for lossless compression.


page 5

page 13

page 14


Discrete Denoising Flows

Discrete flow-based models are a recently proposed class of generative m...

Fast Lossless Neural Compression with Integer-Only Discrete Flows

By applying entropy codecs with learned data distributions, neural compr...

Integer Discrete Flows and Lossless Compression

Lossless compression methods shorten the expected representation size of...

Latent Transformations for Discrete-Data Normalising Flows

Normalising flows (NFs) for discrete data are challenging because parame...

Accounting for Uncertainty When Estimating Counts Through an Average Rounded to the Nearest Integer

In practice, the use of rounding is ubiquitous. Although researchers hav...

Latent Normalizing Flows for Discrete Sequences

Normalizing flows have been shown to be a powerful class of generative m...

Combining Fuzzy Cognitive Maps and Discrete Random Variables

In this paper we propose an extension to the Fuzzy Cognitive Maps (FCMs)...

Please sign up or login with your details

Forgot password? Click here to reset