Towards Empirical Sandwich Bounds on the Rate-Distortion Function

Abstract

Rate-distortion (R-D) function, a key quantity in information theory, characterizes the fundamental limit of how much a data source can be compressed subject to a fidelity criterion, by any compression algorithm. As researchers push for ever-improving compression performance, establishing the R-D function of a given data source is not only of scientific interest, but also sheds light on the possible room for improving compression algorithms. Previous work on this problem relied on distributional assumptions on the data source (Gibson, 2017) or only applied to discrete data (Blahut, 1972; Arimoto, 1972). By contrast, this paper makes the first attempt at an algorithm for sandwiching the R-D function of a general (not necessarily discrete) source requiring only i.i.d. data samples. We estimate R-D sandwich bounds for a variety of artificial and real-world data sources, in settings far beyond the feasibility of any known method, and shed light on the optimality of neural data compression (Ballé et al., 2021; Yang et al., 2022). Our R-D upper bound on natural images indicates theoretical room for improving state-of-the-art image compression methods by at least one dB in PSNR at various bitrates. Our data and code can be found at https://github.com/mandt-lab/empirical-RD-sandwich.

arXiv commentICLR 2022 camera-ready version

References in corpus (18)

• Auto-Encoding Variational Bayes
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Categorical Reparameterization with Gumbel-Softmax
• The information bottleneck method
• Conditional Image Generation with PixelCNN Decoders
• Variational image compression with a scale hyperprior
• Normalizing Flows: An Introduction and Review of Current Methods
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Joint Autoregressive and Hierarchical Priors for Learned Image Compression
• On Variational Bounds of Mutual Information
• Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
• Improving Inference for Neural Image Compression
• Practical Lossless Compression with Latent Variables using Bits Back Coding
• Compression with Flows via Local Bits-Back Coding
• The Intrinsic Dimension of Images and Its Impact on Learning
• Estimation of the Rate-Distortion Function
• Evaluating Lossy Compression Rates of Deep Generative Models
• Finding the Mode of a Kernel Density Estimate