The Curse Revisited: When are Distances Informative for the Ground Truth in Noisy High-Dimensional Data?
This addresses a foundational issue in machine learning for researchers and practitioners dealing with high-dimensional noisy data, providing theoretical insights that are incremental but clarify existing debates.
The paper tackles the problem of whether distances remain informative for ground truth in noisy high-dimensional data, finding that under specific conditions, empirical neighborhood relations can still be truthful even when distance concentration occurs, with empirical verification showing a phase shift aligning with performance changes in dimensionality reduction methods.
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 empirical closest and furthest neighbors away from the ground truth. In this paper, we exactly characterize such effects in noisy high-dimensional data using an asymptotic probabilistic expression. Previously, it has been argued that neighborhood queries become meaningless and unstable when distance concentration occurs, which means that there is a poor relative discrimination between the furthest and closest neighbors in the data. However, we conclude that this is not necessarily the case when we decompose the data in a ground truth -- which we aim to recover -- and noise component. More specifically, we derive that under particular conditions, empirical neighborhood relations affected by noise are still likely to be truthful even when distance concentration occurs. We also include thorough empirical verification of our results, as well as interesting experiments in which our derived 'phase shift' where neighbors become random or not turns out to be identical to the phase shift where common dimensionality reduction methods perform poorly or well for recovering low-dimensional reconstructions of high-dimensional data with dense noise.