2022
The Curse Revisited: When are Distances Informative for the Ground Truth in Noisy High-Dimensional Data?
AISTATS 2022poster
Distances between data points are widely used in machine learning applications. Yet, when corrupted by noise, these distances—and thus the models based upon them—may lose their usefulness in high dimensions. Indeed, the small marginal effects of the noise may then accumulate quickly, shifting empiri…