Sparse Robust Classification via the Kernel Mean
This work addresses the complexity and interpretability issues in kernel classification methods, offering a simpler alternative for practitioners.
The paper tackles the problem of simplifying kernel-based classification by proposing a rule that uses equal weights (the mean) instead of optimizing complex weights, and shows that this approach is consistent, robust, and can be sparsified.
Many leading classification algorithms output a classifier that is a weighted average of kernel evaluations. Optimizing these weights is a nontrivial problem that still attracts much research effort. Furthermore, explaining these methods to the uninitiated is a difficult task. Letting all the weights be equal leads to a conceptually simpler classification rule, one that requires little effort to motivate or explain, the mean. Here we explore the consistency, robustness and sparsification of this simple classification rule.