Zobrazeno 1 - 10
of 267
pro vyhledávání: '"Ye, Jane"'
In this paper we derive new second-order optimality conditions for a very general set-constrained optimization problem where the underlying set may be nononvex. We consider local optimality in specific directions (i.e., optimal in a directional neigh
Externí odkaz:
http://arxiv.org/abs/2404.17696
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 mathematical program with complementarity constraint (MPCC). It is known tha
Externí odkaz:
http://arxiv.org/abs/2311.14857
Autor:
Bai, Kuang, Ye, Jane
This paper is concerned with the directional derivative of the value function for a very general set-constrained optimization problem under perturbation. Under reasonable assumptions, we obtain upper and lower estimates for the upper and lower Dini d
Externí odkaz:
http://arxiv.org/abs/2311.03604
Nonconvex-nonconcave minimax problems have found numerous applications in various fields including machine learning. However, questions remain about what is a good surrogate for local minimax optimum and how to characterize the minimax optimality. Re
Externí odkaz:
http://arxiv.org/abs/2306.17443
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-based difference of convex algorithm was introduced to address bilevel pro
Externí odkaz:
http://arxiv.org/abs/2306.16761
This paper studies bilevel polynomial optimization in which lower level constraining functions depend linearly on lower level variables. We show that such a bilevel program can be reformulated as a disjunctive program using partial Lagrange multiplie
Externí odkaz:
http://arxiv.org/abs/2304.00695
We typically construct optimal designs based on a single objective function. To better capture the breadth of an experiment's goals, we could instead construct a multiple objective optimal design based on multiple objective functions. While algorithm
Externí odkaz:
http://arxiv.org/abs/2303.04746
Autor:
Bai, Kuang, Ye, Jane J.
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 upper estimates for the directional limiting and singular subdifferenti
Externí odkaz:
http://arxiv.org/abs/2211.12597
Autor:
Xiao, Zhuoyu, Ye, Jane J.
The cardinality constrained optimization problem (CCOP) is an optimization problem where the maximum number of nonzero components of any feasible point is bounded. In this paper, we consider CCOP as a mathematical program with disjunctive subspaces c
Externí odkaz:
http://arxiv.org/abs/2209.08428
Gradient-based optimization methods for hyperparameter tuning guarantee theoretical convergence to stationary solutions when for fixed upper-level variable values, the lower level of the bilevel program is strongly convex (LLSC) and smooth (LLS). Thi
Externí odkaz:
http://arxiv.org/abs/2206.05976