Yoichi Izunaga

A Unifying View of Distributionally Robust Optimization for Probability Smoothing via Maximum Entropy

The probability smoothing problem seeks estimators that assign positive probability to all categories, including those unobserved in a finite sample. In our previous work, we established that the estimator derived from distributionally robust optimization (DRO) with a $q$-norm ambiguity set ($q$-DRO) satisfies the axio...