中文
相关论文

相关论文: Optimal Potential Shaping on SE(3) via Neural ODEs…

200 篇论文

The need for fast and robust optimization algorithms are of critical importance in all areas of machine learning. This paper treats the task of designing optimization algorithms as an optimal control problem. Using regret as a metric for an…

机器学习 · 计算机科学 2021-01-21 Philippe Casgrain , Anastasis Kratsios

A wide range of modern science and engineering applications are formulated as optimization problems with a system of partial differential equations (PDEs) as constraints. These PDE-constrained optimization problems are typically solved in a…

人工智能 · 计算机科学 2021-04-28 Yuyu Zhang , Heng Chi , Binghong Chen , Tsz Ling Elaine Tang , Lucia Mirabella , Le Song , Glaucio H. Paulino

We introduce Neural Optimal Design of Experiments, a learning-based framework for optimal experimental design in inverse problems that avoids classical bilevel optimization and indirect sparsity regularization. NODE jointly trains a neural…

机器学习 · 计算机科学 2026-01-08 John E. Darges , Babak Maboudi Afkham , Matthias Chung

The advent of deep learning has yielded powerful tools to automatically compute gradients of computations. This is because training a neural network equates to iteratively updating its parameters using gradient descent to find the minimum…

数据分析、统计与概率 · 物理学 2023-03-01 Nathan Simpson , Lukas Heinrich

To better understand and improve the behavior of neural networks, a recent line of works bridged the connection between ordinary differential equations (ODEs) and deep neural networks (DNNs). The connections are made in two folds: (1) View…

机器学习 · 计算机科学 2019-11-05 Xinshi Chen

We present a gradient-based optimal-control technique for open quantum systems that utilizes quantum trajectories to simulate the quantum dynamics during optimization. Using trajectories allows for optimizing open systems with less…

量子物理 · 物理学 2019-06-03 Mohamed Abdelhafez , David I. Schuster , Jens Koch

Optimal recursive decomposition (or DR-planning) is crucial for analyzing, designing, solving or finding realizations of geometric constraint sytems. While the optimal DR-planning problem is NP-hard even for general 2D bar-joint constraint…

计算几何 · 计算机科学 2015-07-07 Troy Baker , Meera Sitharam , Menghan Wang , Joel Willoughby

The aim of this work is to present a model reduction technique in the framework of optimal control problems for partial differential equations. We combine two approaches used for reducing the computational cost of the mathematical numerical…

数值分析 · 数学 2023-11-09 Ivan Prusak , Monica Nonino , Davide Torlo , Francesco Ballarin , Gianluigi Rozza

We consider an abstract framework for the numerical solution of optimal control problems (OCPs) subject to partial differential equations (PDEs). Examples include not only the distributed control of elliptic PDEs such as the Poisson…

数值分析 · 数学 2025-05-27 Ulrich Langer , Richard Löscher , Olaf Steinbach , Huidong Yang

Neural Ordinary Differential Equations (ODEs) represent a significant advancement at the intersection of machine learning and dynamical systems, offering a continuous-time analog to discrete neural networks. Despite their promise, deploying…

数值分析 · 数学 2025-06-18 Matteo Caldana , Jan S. Hesthaven

We propose a novel approach for training Physics-enhanced Neural ODEs (PeN-ODEs) by expressing the training process as a dynamic optimization problem. The full model, including neural components, is discretized using a high-order implicit…

机器学习 · 计算机科学 2025-08-07 Linus Langenkamp , Philip Hannebohm , Bernhard Bachmann

This paper addresses the problem of solving a class of nonlinear optimal control problems (OCP) with infinite-dimensional linear state constraints involving Riesz-spectral operators. Each instance within this class has time/control…

最优化与控制 · 数学 2017-10-13 Victor Magron , Christophe Prieur

A promising approach to optimal control of nonlinear systems involves iteratively linearizing the system and solving an optimization problem at each time instant to determine the optimal control input. Since this approach relies on online…

最优化与控制 · 数学 2025-01-30 Anran Li , John P. Swensen , Mehdi Hosseinzadeh

Many physical questions in fluid dynamics can be recast in terms of norm constrained optimisation problems; which in-turn, can be further recast as unconstrained problems on spherical manifolds. Due to the nonlinearities of the governing…

流体动力学 · 物理学 2024-01-17 Paul M Mannix , Calum S Skene , Didier Auroux , Florence Marcotte

In a wide range of applications it is desirable to optimally control a dynamical system with respect to concurrent, potentially competing goals. This gives rise to a multiobjective optimal control problem where, instead of computing a…

最优化与控制 · 数学 2020-12-18 Sebastian Peitz , Sina Ober-Blöbaum , Michael Dellnitz

Residual neural networks can be viewed as the forward Euler discretization of an Ordinary Differential Equation (ODE) with a unit time step. This has recently motivated researchers to explore other discretization approaches and train ODE…

机器学习 · 计算机科学 2019-07-02 Amir Gholami , Kurt Keutzer , George Biros

Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. Existing neural operators, however, often suffer from…

We provide several quantum algorithms for continuous optimization that do not require gradient estimation. Instead, we encode the optimization problem into the dynamics of a physical system and coherently simulate the time evolution. We…

量子物理 · 物理学 2026-03-18 Ahmet Burak Catli , Sophia Simon , Nathan Wiebe

Optimal control problems driven by evolutionary partial differential equations arise in many industrial applications and their numerical solution is known to be a challenging problem. One approach to obtain an optimal feedback control is…

数值分析 · 数学 2023-05-16 Gerhard Kirsten , Luca Saluzzi

Neural ODEs (NODEs) are continuous-time neural networks (NNs) that can process data without the limitation of time intervals. They have advantages in learning and understanding the evolution of complex real dynamics. Many previous works…

机器学习 · 计算机科学 2024-11-05 Wenjie Mei , Dongzhe Zheng , Shihua Li