CMU Researchers Introduce Epiplexity: Rethinking Information for Computationally Bound AI
joecole · x · 2026-08-08
Researchers from CMU and other institutions published a new paper, From Entropy to Epiplexity, addressing the limitations of Shannon information theory and Kolmogorov complexity in evaluating data value for machine learning.
The authors identify three paradoxes in traditional information theory: deterministic transformations cannot increase information; information is independent of data order; and likelihood modeling is merely distribution matching. To resolve these tensions, they introduce Epiplexity, a formalization of information that captures what computationally bounded observers can actually learn from data. The metric isolates structural content while excluding time-bounded entropy, such as unpredictable outputs from pseudorandom number generators.
More from Research
- Harvard and MIT Unveil Research on Simulating the World with 8.3 Billion AI Agents — SRSchmidgall · 2026-08-08
- PaXini Partners with EngineAI to Bring Multidimensional Tactile Sensing to T800 Robots — Scobleizer · 2026-08-08
- Google Scholar Halts Submissions After Paper Hijacks OpenReview to Interact with Reviewers — docmilanfar · 2026-08-08
- Medical AI Leader Daniel Hashimoto to Join Duke Surgery Faculty — Laparoscopes · 2026-08-08
- NVIDIA to Explore World Action Models and the Evolution of Robot Foundation Models — MonaJalal_ · 2026-08-08
- AURORA-LM: A 1B Continuous Diffusion Language Model Trained on Ascend NPU — 机器之心 · 2026-08-08