Partially Informed Stochastic Optimization via Zeroth-Order Residual Tracking
Many optimization problems provide direct access to only part of the gradient, while the remaining component must be inferred from function evaluations. This structure arises in performative prediction, performative reinforcement learning, and bilevel optimization with a black-box lower level. We introduce Partially In...
El Mahdi Chayti, Alireza Mirrokni, Martin Jaggi
· 0 citations