Stochastic separation theorems

The problem of non-iterative one-shot and non-destructive correction of unavoidable mistakes arises in all Artificial Intelligence applications in the real world. Its solution requires robust separation of samples with errors from samples where the system works properly. We demonstrate that in (moderately) high dimension this separation could be achieved with probability close to one by linear discriminants. Based on fundamental properties of measure concentration, we show that for M < a exp(bn) random M-element sets in R-n are linearly separable with probability p, p > 1-upsilon, where 1 > upsilon > 0 is a given small constant. Exact values of a, b > 0 depend on the probability distribution that determines how the random M-element sets are drawn, and on the constant upsilon. These stochastic separation theorems provide a new instrument for the development, analysis, and assessment of machine learning methods and algorithms in high dimension. Theoretical statements are illustrated with numerical examples. (C) 2017 Elsevier Ltd. All rights reserved.