Fractal basin geometry and the limits to predictability and reproducibility in deep learning
Nature Machine Intelligence, Published online: 05 November 2026; doi:10.1038/s42256-026-01336-3Deep learning outcomes are hard to predict and reproduce. Ly and Gong propose fractal basin geometry as a mechanism: starting points leading to different outcomes interweave at arbitrarily fine scales, so greater precision yields little improvement.
Read original on Nature Machine Intelligence ↗