Consider a min-max problem in the form of min<Subscript> xεX </Subscript>max<Subscript>1≤i≤m </Subscript>{f <Subscript> i </Subscript>(x)}. It is well-known that the non-differentiability of the max functionF(x) ≡ max<Subscript>1≤i≤m </Subscript>{f <Subscript> i </Subscript>(x)} presents difficulty in finding an optimal solution. An entropic regularization procedure provides a smooth...</subscript></subscript></subscript></subscript></subscript>

Consider a min-max problem in the form of min xεX max 1≤i≤m {f i (x)}. It is well-known that the non-differentiability of the max functionF(x) ≡ max 1≤i≤m {f i (x)} presents difficulty in finding an optimal solution. An entropic regularization procedure provides a smooth...