7 citations · 10 across the 7 of their papers we have counts for
8 papers
Directional Optimality Conditions for Optimization Problems in Asplund Spaces
Weihao Mao, Jane J. Ye
This paper develops directional necessary optimality conditions for constrained optimization problems in Asplund spaces. Under directional metric subregularity, we first derive a d…
Directional Subdifferentials of the Value Function in Asplund Spaces
Weihao Mao, Jane J. Ye
Directional subdifferentials of the value function provide a quantitative measure of optimal value response to perturbations. While existing results are largely limited to finite-d…
Optimality conditions for bilevel programs via Moreau envelope reformulation
Kuang Bai, Jane Ye, Shangzhi Zeng
For bilevel programs with a convex lower level program, the classical approach replaces the lower level program with its Karush-Kuhn-Tucker condition and solve the resulting mathem…
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
Lucy L. Gao, Jane J. Ye, Haian Yin +2
Bilevel programming has emerged as a valuable tool for hyperparameter selection, a central concern in machine learning. In a recent study by Ye et al. (2023), a value function-base…
Directional subdifferential of the value function
Kuang Bai, Jane J. Ye
The directional subdifferential of the value function gives an estimate on how much the optimal value changes under a perturbation in a certain direction. In this paper we derive u…
Value Function Based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems
Lucy Gao, Jane J. Ye, Haian Yin +2
Gradient-based optimization methods for hyperparameter tuning guarantee theoretical convergence to stationary solutions when for fixed upper-level variable values, the lower level…
Directional quasi/pseudo-normality as sufficient conditions for metric subregularity
Kuang Bai, Jane Ye, Jin Zhang
In this paper we study sufficient conditions for metric subregularity of a set-valued map which is the sum of a single-valued continuous map and a locally closed subset. First we d…
Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis
Xiangfeng Wang, Jane Ye, Xiaoming Yuan +2
We develop new perturbation techniques for conducting convergence analysis of various first-order algorithms for a class of nonsmooth optimization problems. We consider the iterati…