English
Related papers

Related papers: KKT-Informed Neural Network

200 papers

We develop refined Karush-Kuhn-Tucker (KKT) and Fritz-John (FJ)-type optimality conditions for nonsmooth, nonconvex mathematical pro\-gra\-mming problems. We pay special attention in the case that the functional constraint belongs to a…

Optimization and Control · Mathematics 2026-04-15 Felipe Lara , Alberto Ramos

We present a learning-based approach to computing solutions for certain NP-hard problems. Our approach combines deep learning techniques with useful algorithmic elements from classic heuristics. The central component is a graph…

Machine Learning · Computer Science 2018-10-26 Zhuwen Li , Qifeng Chen , Vladlen Koltun

We develop an analytical framework to characterize the set of optimal ReLU neural networks by reformulating the non-convex training problem as a convex program. We show that the global optima of the convex parameterization are given by a…

Machine Learning · Computer Science 2024-01-22 Aaron Mishkin , Mert Pilanci

Our aim in this article is two-fold. We use the Charnes-Cooper scalarization technique to develop KKT type conditions to completely characterize Pareto minimizers of convex vector optimization problems and further, we use that scalarization…

Optimization and Control · Mathematics 2019-09-04 Poonam Kesarwani , Joydeep Dutta

The aim of this paper is to develop a general framework for training neural networks (NNs) in a distributed environment, where training data is partitioned over a set of agents that communicate with each other through a sparse, possibly…

Machine Learning · Statistics 2017-04-21 Simone Scardapane , Paolo Di Lorenzo

The idea of embedding optimization problems into deep neural networks as optimization layers to encode constraints and inductive priors has taken hold in recent years. Most existing methods focus on implicitly differentiating…

Machine Learning · Computer Science 2023-04-25 Haixiang Sun , Ye Shi , Jingya Wang , Hoang Duong Tuan , H. Vincent Poor , Dacheng Tao

We present a novel approach to modelling and learning vector fields from physical systems using neural networks that explicitly satisfy known linear operator constraints. To achieve this, the target function is modelled as a linear…

Machine Learning · Statistics 2021-04-29 Johannes Hendriks , Carl Jidling , Adrian Wills , Thomas Schön

Twin neural network regression is trained to predict differences between regression targets rather than the targets themselves. A solution to the original regression problem can be obtained by ensembling predicted differences between the…

Machine Learning · Computer Science 2023-10-03 Sebastian J. Wetzel

We consider a convex optimization problem with many linear inequality constraints. To deal with a large number of constraints, we provide a penalty reformulation of the problem, where the penalty is a variant of the one-sided Huber loss…

Optimization and Control · Mathematics 2023-11-03 Angelia Nedich , Tatiana Tatarenko

In this paper, a robust sequential quadratic programming method for constrained optimization is generalized to problem with an {expectation} objective function {and} deterministic equality and inequality constraints. A stochastic line…

Optimization and Control · Mathematics 2024-10-07 Songqiang Qiu , Vyacheslav Kungurtsev

Recurrent Neural Networks (RNNs) are widely used to model sequential data in a wide range of areas, such as natural language processing, speech recognition, machine translation, and time series analysis. In this paper, we model the training…

Optimization and Control · Mathematics 2024-08-20 Yue Wang , Chao Zhang , Xiaojun Chen

Constrained optimization with multiple functional inequality constraints has significant applications in machine learning. This paper examines a crucial subset of such problems where both the objective and constraint functions are weakly…

Machine Learning · Computer Science 2026-02-09 Ming Yang , Gang Li , Quanqi Hu , Qihang Lin , Tianbao Yang

We consider robust combinatorial optimization problems where the decision maker can react to a scenario by choosing from a finite set of $k$ solutions. This approach is appropriate for decision problems under uncertainty where the…

Optimization and Control · Mathematics 2019-03-28 André Chassein , Marc Goerigk , Jannis Kurtz , Michael Poss

Second-order optimality conditions for vector nonlinear programming problems with inequality constraints are studied in this paper. We introduce a new second-order constraint qualification, which includes Mangasarian-Fromovitz constraint…

Optimization and Control · Mathematics 2019-06-11 Vsevolod I. Ivanov

We extend in two ways the standard Karush-Kuhn-Tucker optimality conditions to problems with a convex objective, convex functional constraints, and the extra requirement that some of the variables must be integral. While the standard…

Optimization and Control · Mathematics 2014-12-09 Michel Baes , Timm Oertel , Robert Weismantel

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In…

Due to the multi-linearity of tensors, most algorithms for tensor optimization problems are designed based on the block coordinate descent method. Such algorithms are widely employed by practitioners for their implementability and…

Optimization and Control · Mathematics 2022-01-14 Ke Ye , Shenglong Hu

We propose a regularized saddle-point algorithm for convex networked optimization problems with resource allocation constraints. Standard distributed gradient methods suffer from slow convergence and require excessive communication when…

Systems and Control · Computer Science 2012-08-16 Andrea Simonetto , Tamas Keviczky , Mikael Johansson

This work concerns the local convergence theory of Newton and quasi-Newton methods for convex-composite optimization: minimize f(x):=h(c(x)), where h is an infinite-valued proper convex function and c is C^2-smooth. We focus on the case…

Optimization and Control · Mathematics 2018-06-19 James V. Burke , Abraham Engle

Control of complex systems involves both system identification and controller design. Deep neural networks have proven to be successful in many identification tasks, however, from model-based control perspective, these networks are…

Optimization and Control · Mathematics 2019-02-28 Yize Chen , Yuanyuan Shi , Baosen Zhang