4 papers · 1 filter
Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints
Cac Phan, Kai Wang
This work provides the first finite-time convergence guarantees for linearly constrained stochastic bilevel optimization using only first-order methods, requiring solely gradient i…
Finding a Multiple Follower Stackelberg Equilibrium: A Fully First-Order Method
April Niu, Kai Wang, Juba Ziani
In this work, we propose the first fully first-order method to compute an epsilon stationary Stackelberg equilibrium with convergence guarantees. To achieve this, we first reframe…
Convergence analysis of nonmonotone proximal gradient methods under local Lipschitz continuity and Kurdyka--Åojasiewicz property
Xiaoxi Jia, Kai Wang
The proximal gradient method is a standard approach for solving composite minimization problems in which the objective function is the sum of a continuously differentiable function…
First-Order Methods for Linearly Constrained Bilevel Optimization
Guy Kornowski, Swati Padmanabhan, Kai Wang +2
Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for unconstrained b…