Asymptotic Supervised Predictive Classifiers under Partition Exchangeability
This result is incremental for practitioners in machine learning, as it provides theoretical justification for using simpler classifiers with large datasets to reduce computational costs.
The paper tackles the problem of classifier convergence in supervised classification under partition exchangeability, showing that simultaneous and marginal predictive classifiers become asymptotically equivalent with infinite data, allowing substitution of simpler marginal classifiers for more computationally expensive simultaneous ones.
The convergence of simultaneous and marginal predictive classifiers under partition exchangeability in supervised classification is obtained. The result shows the asymptotic convergence of these classifiers under infinite amount of training or test data, such that after observing umpteen amount of data, the differences between these classifiers would be negligible. This is an important result from the practical perspective as under the presence of sufficiently large amount of data, one can replace the simpler marginal classifier with computationally more expensive simultaneous one.