Robust Bayesian Classification Using an Optimistic Score Ratio
This work addresses robust classification for scenarios with limited contextual data, representing an incremental improvement in Bayesian methods.
The paper tackles robust binary classification with limited information on class-conditional distributions by proposing a Bayesian classifier using an optimistic score ratio, which searches for the most plausible distribution within a constrained ambiguity set and demonstrates solid statistical guarantees and computational tractability on synthetic and empirical data.
We build a Bayesian contextual classification model using an optimistic score ratio for robust binary classification when there is limited information on the class-conditional, or contextual, distribution. The optimistic score searches for the distribution that is most plausible to explain the observed outcomes in the testing sample among all distributions belonging to the contextual ambiguity set which is prescribed using a limited structural constraint on the mean vector and the covariance matrix of the underlying contextual distribution. We show that the Bayesian classifier using the optimistic score ratio is conceptually attractive, delivers solid statistical guarantees and is computationally tractable. We showcase the power of the proposed optimistic score ratio classifier on both synthetic and empirical data.