English
Related papers

Related papers: KKT-Informed Neural Network

200 papers

We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly represent both the support and gauge functions of a convex body. We prove a universal…

Optimization and Control · Mathematics 2026-05-06 Eloi Martinet

Recently, theoretical analyses of deep neural networks have broadly focused on two directions: 1) Providing insight into neural network training by SGD in the limit of infinite hidden-layer width and infinitesimally small learning rate…

Machine Learning · Computer Science 2023-09-27 Rajat Vadiraj Dwaraknath , Tolga Ergen , Mert Pilanci

Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training neural networks is a challenging task in many applications. The prevalent…

Optimization and Control · Mathematics 2022-10-28 Patrick L. Combettes , Jean-Christophe Pesquet , Audrey Repetti

Quadratic constrained quadratic programming problems often occur in various fields such as engineering practice, management science, and network communication. This article mainly studies a non convex quadratic programming problem with…

Optimization and Control · Mathematics 2023-12-29 Bo Zhang , YueLin Gao , Xia Liu , XiaoLi Huang

In this document, a neural network is employed in order to estimate the solution of the initial value problem in the context of non linear trajectories. Such trajectories can be subject to gravity, thrust, drag, centrifugal force,…

Machine Learning · Computer Science 2021-07-21 Theodoros Ntakouris

This paper addresses the analysis and design of quadratic neural networks, which have been recently introduced in the literature, and their applications to regression, classification, system identification and control of dynamical systems.…

Machine Learning · Computer Science 2022-07-28 Luis Rodrigues , Sidney Givigi

For quasi-linear interface problems with discontinuous diffusion coefficients, the nonconvex objective functional often leads to optimization stagnation in randomized neural network approximations. This paper Proposes a…

Numerical Analysis · Mathematics 2026-02-06 Siyuan Lang , Zhiyue Zhang

In the area of physical simulations, nearly all neural-network-based methods directly predict future states from the input states. However, many traditional simulation engines instead model the constraints of the system and select the state…

Machine Learning · Computer Science 2022-01-31 Yulia Rubanova , Alvaro Sanchez-Gonzalez , Tobias Pfaff , Peter Battaglia

Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However,…

This paper presents a canonical duality theory for solving a general nonconvex constrained optimization problem within a unified framework to cover Lagrange multiplier method and KKT theory. It is proved that if both target function and…

Optimization and Control · Mathematics 2013-10-09 Vittorio Latorre , David Y. Gao

This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city…

Artificial Intelligence · Computer Science 2017-01-16 Irwan Bello , Hieu Pham , Quoc V. Le , Mohammad Norouzi , Samy Bengio

In recent years, artificial neural networks have achieved state-of-the-art performance for predicting the responses of neurons in the visual cortex to natural stimuli. However, they require a time consuming parameter optimization process…

Neurons and Cognition · Quantitative Biology 2020-10-24 R. James Cotton , Fabian H. Sinz , Andreas S. Tolias

We propose a new approach to learned optimization where we represent the computation of an optimizer's update step using a neural network. The parameters of the optimizer are then learned by training on a set of optimization tasks with the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-29 Erik Gärtner , Luke Metz , Mykhaylo Andriluka , C. Daniel Freeman , Cristian Sminchisescu

In this paper we propose a framework for solving constrained online convex optimization problem. Our motivation stems from the observation that most algorithms proposed for online convex optimization require a projection onto the convex set…

Machine Learning · Computer Science 2012-10-01 Mehrdad Mahdavi , Rong Jin , Tianbao Yang

Parametric optimization solves a family of optimization problems as a function of parameters. It is a critical component in situations where optimal decision making is repeatedly performed for updated parameter values, but computation…

Optimization and Control · Mathematics 2023-08-22 Hyunglip Bae , Jang Ho Kim , Woo Chang Kim

Emerging edge computing paradigms enable heterogeneous devices to collaborate on complex computation applications. However, for congestible links and computing units, delay-optimal forwarding and offloading for service chain tasks (e.g.,…

Networking and Internet Architecture · Computer Science 2024-03-26 Jinkun Zhang , Yuezhou Liu , Edmund Yeh

Recently, message-passing graph neural networks (MPNNs) have shown potential for solving combinatorial and continuous optimization problems due to their ability to capture variable-constraint interactions. While existing approaches leverage…

Artificial Intelligence · Computer Science 2025-02-05 Chendi Qian , Christopher Morris

In this paper we study a broad class of structured nonlinear programming (SNLP) problems. In particular, we first establish the first-order optimality conditions for them. Then we propose sequential convex programming (SCP) methods for…

Optimization and Control · Mathematics 2022-06-22 Zhaosong Lu

This study introduces a novel approach to ensure the existence and uniqueness of optimal parameters in neural networks. The paper details how a recurrent neural networks (RNN) can be transformed into a contraction in a domain where its…

Machine Learning · Statistics 2024-06-21 Valdes Gonzalo

In the realm of robust optimization the k-adaptability approach is one promising method to derive approximate solutions for two-stage robust optimization problems. Instead of allowing all possible second-stage decisions, the k-adaptability…

Optimization and Control · Mathematics 2025-09-04 Jannis Kurtz