Timezone: »

Lossy Compression for Lossless Prediction
Yann Dubois · Benjamin Bloem-Reddy · Karen Ullrich · Chris Maddison

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @

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 1000x on ImageNet) compared to JPEG on 8 datasets, without decreasing downstream classification performance.

Author Information

Yann Dubois (Stanford University)
Benjamin Bloem-Reddy (University of British Columbia)
Karen Ullrich (Facebook AI Research)

Research scientist (s/h) at FAIR NY + collab. w/ Vector Institute. ❤️ Deep Learning + Information Theory. Previously, Machine Learning PhD at UoAmsterdam.

Chris Maddison (University of Toronto)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors