activity
20182026
most citedTowards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond

13 citations · 36 across the 17 of their papers we have counts for

collaborators

21 papers

math.OC2026

Limiting Stationarity of Regularized Gap-Function Reformulations for Bilevel Optimization with Unbounded Multipliers

Xiaoning Bai, Shangzhi Zeng, Jin Zhang

Value-function-type reformulations have generated a broad class of methods for bilevel optimization. However, the corresponding value-function-type constraints are inherently degen…

math.OC2026

A Single-Loop Penalty-based Algorithm for Stochastic Minimax Optimization with Nonlinear Coupled Constraints

Qichao Cao, Shangzhi Zeng, Jin Zhang +1

We study stochastic nonconvex-concave minimax optimization with nonlinear coupled constraints that are convex in the maximization variable. To address the nonsmoothness arising fro…

math.OC2026

A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems

Yongcun Song, Shangzhi Zeng, Jin Zhang +1

Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonlinearity, and bilevel structure. Classi…

math.OC2025

A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation

Qichao Cao, Shangzhi Zeng, Jin Zhang

Bilevel optimization has garnered significant attention in the machine learning community recently, particularly regarding the development of efficient numerical methods. While sub…

math.OC2025

Prox-PINNs: A Deep Learning Algorithmic Framework for Elliptic Variational Inequalities

Yu Gao, Yongcun Song, Zhiyu Tan +2

Elliptic variational inequalities (EVIs) present significant challenges in numerical computation due to their inherent non-smoothness, nonlinearity, and inequality formulations. Tr…

math.OC2025

Extended SQP Methods in Nonsmooth Difference Programming Applied to Problems with Variational Inequality Constraints

Boris S. Mordukhovich, Yixia Song, Shangzhi Zeng +1

This paper explores a new class of constrained difference programming problems, where the objective and constraints are formulated as differences of functions, without requiring th…