Yann LeCun on the Curse of Dimensionality: A Universal Challenge in ML

ylecun · x · 2026-08-23

Yann LeCun responded to a discussion about the "curse of dimensionality." He noted that while the term originated with histograms—which require massive amounts of data to fill the space as dimensions increase—it actually impacts every machine learning method. This manifests either as increased memory footprint, higher computational requirements, or a larger training set size needed to achieve a given level of performance.

Related event: LeCun on the Curse of Dimensionality: High-Dimensional Parameter Space Helps(2 posts)→

Original post →

More from Research

Research channel →