English
Related papers

Related papers: Training neural networks under physical constraint…

200 papers

The Sequential Linear Quadratic (SLQ) algorithm is a continuous-time variant of the well-known Differential Dynamic Programming (DDP) technique with a Gauss-Newton Hessian approximation. This family of methods has gained popularity in the…

Robotics · Computer Science 2021-03-29 Jean-Pierre Sleiman , Farbod Farshidian , Marco Hutter

Physics-informed neural networks (PINNs) often struggle with multi-scale PDEs featuring sharp gradients and nontrivial boundary conditions, as the physics residual and boundary enforcement compete during optimization. We present a…

Numerical Analysis · Mathematics 2025-12-01 Naseem Abbas , Vittorio Colao , Davide Macri , William Spataro

Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal…

Machine Learning · Computer Science 2025-01-28 Tianqi Zhang , Puzhen Yuan , Guojian Zhan , Ziyu Lin , Yao Lyu , Zhenzhi Qin , Jingliang Duan , Liping Zhang , Shengbo Eben Li

A novel augmented Lagrangian method for solving non-convex programs with nonlinear cost and constraint couplings in a distributed framework is presented. The proposed decomposition algorithm is made of two layers: The outer level is a…

Optimization and Control · Mathematics 2014-07-22 Jean-Hubert Hours , Colin N. Jones

Reasoning about the physical world requires models that are endowed with the right inductive biases to learn the underlying dynamics. Recent works improve generalization for predicting trajectories by learning the Hamiltonian or Lagrangian…

Machine Learning · Computer Science 2020-10-27 Marc Finzi , Ke Alexander Wang , Andrew Gordon Wilson

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we…

Computational Finance · Quantitative Finance 2023-01-16 Pierre Bras , Gilles Pagès

Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and…

Machine Learning · Computer Science 2019-04-18 Jacob Rafati , Roummel F. Marcia

In this paper, we unroll the dynamics of the dual ascent (DA) algorithm in two coupled graph neural networks (GNNs) to solve constrained optimization problems. The two networks interact with each other at the layer level to find a saddle…

Machine Learning · Computer Science 2026-02-03 Samar Hadou , Alejandro Ribeiro

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with…

Machine Learning · Computer Science 2024-12-17 Naoki Sato , Koshiro Izumi , Hideaki Iiduka

Deep neural networks (DNN) have been used to model nonlinear relations between physical quantities. Those DNNs are embedded in physical systems described by partial differential equations (PDE) and trained by minimizing a loss function that…

Numerical Analysis · Mathematics 2020-02-26 Kailai Xu , Eric Darve

Differential Dynamic Programming (DDP) has become a well established method for unconstrained trajectory optimization. Despite its several applications in robotics and controls however, a widely successful constrained version of the…

Optimization and Control · Mathematics 2020-05-05 Yuichiro Aoyama , George Boutselis , Akash Patel , Evangelos A. Theodorou

Lagrangian Neural Networks (LNNs) can learn arbitrary Lagrangians from trajectory data, but their unusual optimization objective leads to significant training instabilities that limit their application to complex systems. We propose several…

Machine Learning · Computer Science 2026-01-21 Abdullah Umut Hamzaogullari , Arkadas Ozakin

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations.…

Machine Learning · Computer Science 2023-11-22 Amanda A Howard , Sarah H Murphy , Shady E Ahmed , Panos Stinis

Recent work has shown that the training of a one-hidden-layer, scalar-output fully-connected ReLU neural network can be reformulated as a finite-dimensional convex program. Unfortunately, the scale of such a convex program grows…

Machine Learning · Computer Science 2021-05-27 Yatong Bai , Tanmay Gautam , Yu Gai , Somayeh Sojoudi

Neural networks have shown great potential in accelerating the solution of partial differential equations (PDEs). Recently, there has been a growing interest in introducing physics constraints into training neural PDE solvers to reduce the…

Machine Learning · Computer Science 2023-05-30 Xinquan Huang , Wenlei Shi , Qi Meng , Yue Wang , Xiaotian Gao , Jia Zhang , Tie-Yan Liu

Lagrangian Neural Networks (LNNs) are a powerful tool for addressing physical systems, particularly those governed by conservation laws. LNNs can parametrize the Lagrangian of a system to predict trajectories with nearly conserved energy.…

Machine Learning · Computer Science 2025-07-29 Viviana Alejandra Diaz , Leandro Martin Salomone , Marcela Zuccalli

We design inexact proximal augmented Lagrangian based decomposition methods for convex composite programming problems with dual block-angular structures. Our methods are particularly well suited for convex quadratic programming problems…

Optimization and Control · Mathematics 2023-03-14 Kuang-Yu Ding , Xin-Yee Lam , Kim-Chuan Toh

Recent progress on deep learning relies heavily on the quality and efficiency of training algorithms. In this paper, we develop a fast training method motivated by the nonlinear Conjugate Gradient (CG) framework. We propose the Conjugate…

Machine Learning · Computer Science 2021-07-28 Zhiyong Hao , Yixuan Jiang , Huihua Yu , Hsiao-Dong Chiang

The Fokker-Plank-Kolmogorov (FPK) equation is an idealized model representing many stochastic systems commonly encountered in the analysis of stochastic structures as well as many other applications. Its solution thus provides an invaluable…

Machine Learning · Computer Science 2023-11-09 Amir H. Khodabakhsh , Seid H. Pourtakdoust

In this paper, a projected primal-dual gradient flow of augmented Lagrangian is presented to solve convex optimization problems that are not necessarily strictly convex. The optimization variables are restricted by a convex set with…

Optimization and Control · Mathematics 2018-10-31 Han Zhang , Jieqiang Wei , Peng Yi , Xiaoming Hu
‹ Prev 1 3 4 5 6 7 10 Next ›