Communication systems to date primarily aim at reliably communicating bit sequences.
Such an approach provides efficient engineering designs that are agnostic to the meanings …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

This paper outlines an end-to-end optimized lossy image compression framework using
diffusion generative models. The approach relies on the transform coding paradigm, where …

Change-of-variables (CoV) formulas allow to reduce complicated probability densities to
simpler ones by a learned transformation with tractable Jacobian determinant. They are thus …

Relative entropy coding (REC) algorithms encode a sample from a target distribution $ Q $
using a proposal distribution $ P $ using as few bits as possible. Unlike entropy coding, REC …

Rate-distortion-perception theory extends Shannon's rate-distortion theory by introducing a
constraint on the perceptual quality of the output. The perception constraint complements the …

A popular approach to learning encoders for lossy compression is to use additive uniform
noise during training as a differentiable approximation to test-time quantization. We …

Compressing the output of $\epsilon $-locally differentially private (LDP) randomizers
naively leads to suboptimal utility. In this work, we demonstrate the benefits of using …

Relative entropy coding (REC) algorithms encode a sample from a target distribution Q
using a proposal distribution P, such that the expected codelength is O (KL [Q|| P]). REC can …

The efficient communication of noisy data has applications in several areas of machine
learning, such as neural compression or differential privacy, and is also known as reverse …