Mika et al. (1999) introduce a non-linear formulation of Fisher's linear discriminant, based the now familiar "kernel trick", demonstrating state-of-the-art performance on a wide range of real-world benchmark datasets. In this paper, we show that the usual regularisation parameter can be adjusted so as to minimise the leave-one-out cross-validation error with a computational complexity of only O(l2) operations, where l is the number of training patterns, rather than the O(l4) operations required for a naive implementation of the leave-one-out procedure. This procedure is then used to form a component of an efficient hierarchical model selection strategy where the regularisation parameter is optimised within the inner loop while the kernel parameters are optimised in the outer loop.
|Number of pages||4|
|Publication status||Published - Aug 2004|
|Event||Proceedings of the 17th International Conference on Pattern Recognition (ICPR-2004) - |
Duration: 23 Aug 2004 → 26 Aug 2004
|Conference||Proceedings of the 17th International Conference on Pattern Recognition (ICPR-2004)|
|Period||23/08/04 → 26/08/04|