2020
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
ICML 2020poster
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimat…