Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize the bit-rate required to ensure high performance on all predictive tasks that are invariant under a set of transformations, such as data augmentations. Based on our theory, we design unsupervised objectives for training neural compressors. Using these objectives, we train a generic image compressor that achieves substantial rate savings (more than 1000× on ImageNet) compared to JPEG on 8 datasets, without decreasing downstream classification performance.
@article{arxiv.2106.10800,
title = {Lossy Compression for Lossless Prediction},
author = {Yann Dubois and Benjamin Bloem-Reddy and Karen Ullrich and Chris J. Maddison},
journal= {arXiv preprint arXiv:2106.10800},
year = {2022}
}