An Impossibility Result for High Dimensional Supervised Learning
This reveals a fundamental limitation for machine learning practitioners in high-dimensional, small-sample settings, emphasizing the need for prior knowledge like sparsity.
The paper demonstrates that in high-dimensional supervised classification with Gaussian class densities and more dimensions than samples, the Bayes error can be near zero, yet the minimax error probability for any algorithm is no better than random guessing, highlighting the ineffectiveness of learning without strong structural constraints.
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples. We show that the Bayes error, namely the minimum attainable error probability with complete distributional knowledge and equally likely classes, can be arbitrarily close to zero and yet the limiting minimax error probability of every supervised learning algorithm is no better than a random coin toss. In contrast to related studies where the classification difficulty (Bayes error) is made to vanish, we hold it constant when taking high-dimensional limits. In contrast to VC-dimension based minimax lower bounds that consider the worst case error probability over all distributions that have a fixed Bayes error, our worst case is over the family of Gaussian distributions with constant Bayes error. We also show that a nontrivial asymptotic minimax error probability can only be attained for parametric subsets of zero measure (in a suitable measure space). These results expose the fundamental importance of prior knowledge and suggest that unless we impose strong structural constraints, such as sparsity, on the parametric space, supervised learning may be ineffective in high dimensional small sample settings.