RandomBoost: Simplified Multi-class Boosting through Randomization
This addresses the computational burden of multi-class classification for machine learning practitioners, though it appears incremental as it builds on existing boosting frameworks.
The paper tackles the problem of multi-class classification by proposing RandomBoost, which uses random projections to reduce the need for multiple binary classifiers, resulting in a single vector-valued parameter regardless of class count. Experiments show it compares favorably to existing methods in convergence rate and classification accuracy.
We propose a novel boosting approach to multi-class classification problems, in which multiple classes are distinguished by a set of random projection matrices in essence. The approach uses random projections to alleviate the proliferation of binary classifiers typically required to perform multi-class classification. The result is a multi-class classifier with a single vector-valued parameter, irrespective of the number of classes involved. Two variants of this approach are proposed. The first method randomly projects the original data into new spaces, while the second method randomly projects the outputs of learned weak classifiers. These methods are not only conceptually simple but also effective and easy to implement. A series of experiments on synthetic, machine learning and visual recognition data sets demonstrate that our proposed methods compare favorably to existing multi-class boosting algorithms in terms of both the convergence rate and classification accuracy.