DeepAI AI Chat
Log In Sign Up

On the advantages of stochastic encoders

by   Lucas Theis, et al.

Stochastic encoders have been used in rate-distortion theory and neural compression because they can be easier to handle. However, in performance comparisons with deterministic encoders they often do worse, suggesting that noise in the encoding process may generally be a bad idea. It is poorly understood if and when stochastic encoders do better than deterministic encoders. In this paper we provide one illustrative example which shows that stochastic encoders can significantly outperform the best deterministic encoders. Our toy example suggests that stochastic encoders may be particularly useful in the regime of "perfect perceptual quality".


page 1

page 2

page 3

page 4


On the Latent Space of Wasserstein Auto-Encoders

We study the role of latent space dimensionality in Wasserstein auto-enc...

A coding theorem for the rate-distortion-perception function

The rate-distortion-perception function (RDPF; Blau and Michaeli, 2019) ...

Encoding Data for HTM Systems

Hierarchical Temporal Memory (HTM) is a biologically inspired machine in...

Robust Distributed Compression of Symmetrically Correlated Gaussian Sources

Consider a lossy compression system with ℓ distributed encoders and a ce...

Object Detection-Based Variable Quantization Processing

In this paper, we propose a preprocessing method for conventional image ...

Self-Organising Stochastic Encoders

The processing of mega-dimensional data, such as images, scales linearly...