中文
相关论文

相关论文: New Constraint Qualifications for Optimization Pro…

200 篇论文

With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy robustness, safety, and fairness…

机器学习 · 计算机科学 2024-03-19 Juan Elenter , Luiz F. O. Chamon , Alejandro Ribeiro

Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint…

最优化与控制 · 数学 2025-03-04 Huimin Li , Yuya Yamakawa , Ellen H. Fukuda , Nobuo Yamashita

Motivated by robotic trajectory optimization problems we consider the Augmented Lagrangian approach to constrained optimization. We first propose an alternative augmentation of the Lagrangian to handle the inequality case (not based on…

最优化与控制 · 数学 2014-12-16 Marc Toussaint

This paper details a novel indirect method for solving constrained optimal control problems (OCPs) directly in continuous-time function space. The KKT conditions are embedded in a non-smooth complementarity function, which enables their…

最优化与控制 · 数学 2026-05-11 Simon J. Jones , Dominic Liao-McPherson , Marco M. Nicotra

This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks. We first generalize existing algebraic characterizations of acyclicity to a class of matrix polynomials. Next, focusing on a…

机器学习 · 计算机科学 2020-10-20 Dennis Wei , Tian Gao , Yue Yu

Bayesian optimisation has proven to be a powerful tool for expensive global black-box optimisation problems. In this paper, we propose new Bayesian optimisation variants of the popular Knowledge Gradient acquisition functions for problems…

机器学习 · 计算机科学 2025-12-22 Xietao Wang Lin , Juan Ungredda , Max Butler , James Town , Alma Rahat , Hemant Singh , Juergen Branke

Solutions to nonlinear, nonconvex optimization problems can fail to satisfy the KKT optimality conditions even when they are optimal. This is due to the fact that unless constraint qualifications (CQ) are satisfied, Lagrange multipliers may…

最优化与控制 · 数学 2020-05-11 Adrian Hauswirth , Saverio Bolognani , Gabriela Hug , Florian Dörfler

In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ($l_1$ norm) and Chebyshev ($\max$ norm). The optimality conditions are based on neural networks with at…

最优化与控制 · 数学 2025-06-24 Vinesha Peiris , Nadezda Sukhorukova , Julien Ugon

We establish necessary conditions of optimality for discrete-time infinite-horizon optimal control in presence of constraints at infinity. These necessary conditions are in form of weak and strong Pontryagin principles. We use a functional…

动力系统 · 数学 2015-11-09 Joel Blot , Thoi Ngo

In this paper we study the worst-case complexity of an inexact Augmented Lagrangian method for nonconvex constrained problems. Assuming that the penalty parameters are bounded, we prove a complexity bound of $\mathcal{O}(|\log(\epsilon)|)$…

最优化与控制 · 数学 2021-05-25 Geovani N. Grapiglia , Ya-xiang Yuan

In this paper, we are concerned with stationarity conditions and qualification conditions for optimization problems with disjunctive constraints. This class covers, among others, optimization problems with complementarity, vanishing, or…

最优化与控制 · 数学 2025-10-14 Isabella Käming , Patrick Mehlitz

The types of constraints encountered in black-box and simulation-based optimization problems differ significantly from those treated in nonlinear programming. We introduce a characterization of constraints to address this situation. We…

最优化与控制 · 数学 2015-06-01 Sébastien Le Digabel , Stefan M. Wild

This paper provides necessary and sufficient optimality conditions for abstract constrained mathematical programming problems in locally convex spaces under new qualification conditions. Our approach exploits the geometrical properties of…

最优化与控制 · 数学 2023-02-10 Rafael Correa , Marco A. López , Pedro Pérez-Aros

Minimax optimization problems are an important class of optimization problems arising from both modern machine learning and from traditional research areas. We focus on the stability of constrained minimax optimization problems based on the…

最优化与控制 · 数学 2021-11-11 Yu-Hong Dai , Liwei Zhang

In this paper, we introduce a kind of approximate Karush--Kuhn--Tucker condition (AKKT) for a smooth cone-constrained vector optimization problem. We show that, without any constraint qualification, the AKKT condition is a necessary for a…

最优化与控制 · 数学 2019-02-21 Nguyen Van Tuyen , Yi-Bin Xiao , Ta Quang Son

In the present paper, we are concerned with a class of constrained vector optimization problems, where the objective functions and active constraint functions are locally Lipschitz at the referee point. Some second-order constraint…

最优化与控制 · 数学 2019-05-14 Yi-Bin Xiao , Nguyen Van Tuyen , Ching-Feng Wen , Jen-Chih Yao

This paper investigates the stochastic linear-quadratic control problems with affine constraints, in which both equality and inequality constraints are involved. With the help of the Pontryagin maximum principle and Lagrangian duality…

最优化与控制 · 数学 2024-04-17 Zhun Gou , Nan-jing Huang , Xian-jun Long , Jian-hao Kang

This study investigates imposing hard inequality constraints on the outputs of convolutional neural networks (CNN) during training. Several recent works showed that the theoretical and practical advantages of Lagrangian optimization over…

计算机视觉与模式识别 · 计算机科学 2023-08-31 Hoel Kervadec , Jose Dolz , Jing Yuan , Christian Desrosiers , Eric Granger , Ismail Ben Ayed

This paper concerns parameterized convex infinite (or semi-infinite) inequality systems whose decision variables run over general infinite-dimensional Banach (resp. finite-dimensional) spaces and that are indexed by an arbitrary fixed set T…

最优化与控制 · 数学 2011-02-07 M. J. CÁnovas , M. A. LÓpez , B. S. Mordukhovich , J. Parra

Asymptotic stationarity and regularity conditions turned out to be quite useful to study the qualitative properties of numerical solution methods for standard nonlinear and complementarity-constrained programs. In this paper, we first…

最优化与控制 · 数学 2021-09-02 Patrick Mehlitz