A result relating convex n-widths to covering numbers with some applications to neural networks
This provides theoretical insights into why neural networks can avoid the curse of dimensionality in pattern recognition, though it is incremental as it builds on existing covering number results.
The paper tackles the problem of approximating high-dimensional function classes with linear combinations of features, showing that for neural networks, covering numbers of single hidden nodes bound the convex core, leading to upper bounds on approximation rates.
In general, approximating classes of functions defined over high-dimensional input spaces by linear combinations of a fixed set of basis functions or ``features'' is known to be hard. Typically, the worst-case error of the best basis set decays only as fast as $Θ\(n^{-1/d}\)$, where $n$ is the number of basis functions and $d$ is the input dimension. However, there are many examples of high-dimensional pattern recognition problems (such as face recognition) where linear combinations of small sets of features do solve the problem well. Hence these function classes do not suffer from the ``curse of dimensionality'' associated with more general classes. It is natural then, to look for characterizations of high-dimensional function classes that nevertheless are approximated well by linear combinations of small sets of features. In this paper we give a general result relating the error of approximation of a function class to the covering number of its ``convex core''. For one-hidden-layer neural networks, covering numbers of the class of functions computed by a single hidden node upper bound the covering numbers of the convex core. Hence, using standard results we obtain upper bounds on the approximation rate of neural network classes.