# Lossy Compression with Distortion Constrained Optimization

arXiv: https://arxiv.org/abs/2005.04064 · HTML: https://mlsanity.com/paper/2005.04064/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2020.

## Built on by (most cited first, 6 of 6)

- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Neural Video Compression using GANs for Detail Synthesis and Propagation](https://mlsanity.com/paper/2107.12038/) (2021)
- [Deep Perceptual Image Quality Assessment for Compression](https://mlsanity.com/paper/2103.01114/) (2021)
- [Substitutional Neural Image Compression](https://mlsanity.com/paper/2105.07512/) (2021)
- [Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval](https://mlsanity.com/paper/2204.13382/) (2022)
- [You've Seen Enough: Quality-Constrained Image Coding for Machines](https://mlsanity.com/paper/2609.25108/) (2026)

## Abstract (arXiv)

When training end-to-end learned models for lossy compression, one has to balance the rate and distortion losses. This is typically done by manually setting a tradeoff parameter β, an approach called β-VAE. Using this approach it is difficult to target a specific rate or distortion value, because the result can be very sensitive to β, and the appropriate value for β depends on the model and problem setup. As a result, model comparison requires extensive per-model β-tuning, and producing a whole rate-distortion curve (by varying β) for each model to be compared. We argue that the constrained optimization method of Rezende and Viola, 2018 is a lot more appropriate for training lossy compression models because it allows us to obtain the best possible rate subject to a distortion constraint. This enables pointwise model comparisons, by training two models with the same distortion target and comparing their rate. We show that the method does manage to satisfy the constraint on a realistic image compression task, outperforms a constrained optimization method based on a hinge-loss, and is more practical to use for model selection than a β-VAE.