SOURCE-LINKED INTELLIGENCE

On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Substantial efforts have been devoted to making deep learning objectives, representations, and architectures interpretable, with the goal of improving the safety, robustness, and generalisation of learning systems in diverse real-world applications. The recently proposed maximal coding rate reduction ($\mathrm{MCR}^{2}$) offers a promising information-theoretic framework for learning structured, discriminative representations of class-wise submanifolds and has inspired interpretable white-box architectures. However, we observe that $\mathrm{MCR}^{2}$ can completely fail under distribution shif

Read original source ↗ Open in workspace

recordType

paper

region

Global