首页/论文/2001.08423

arXiv 2001.084232020-01math.OCcs.NAmath.DSmath.NA

Overcoming the curse of dimensionality for approximating Lyapunov functions with deep neural networks under a small-gain condition

Lars Grüne

备注：: In this version a couple of typos and inaccuracies were fixed. In the previous version version a missing "-" sign in eq. (2) was added (thanks to Sergey Dashkovskiy for spotting this) and three typos were corrected (thanks to Manuel Schaller for reporting them)

英文摘要：

We propose a deep neural network architecture for storing approximate Lyapunov functions of systems of ordinary differential equations. Under a small-gain condition on the system, the number of neurons needed for an approximation of a Lyapunov function with fixed accuracy grows only polynomially in the state dimension, i.e., the proposed approach is able to overcome the curse of dimensionality.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures

We propose new and original mathematical connections between Hamilton-Jacobi (HJ) partial differential equations (PDEs) with initial data and neural network architectures. Specifically, we prove that some classes of neural networks correspond to representation formulas of HJ PDE solutions whose Hamiltonians and initial data are obtained from the parameters of the neural networks. These results do not rely on universal approximation properties of neural networks; rather, our results show that some classes of neural network architectures naturally encode the physics contained in some HJ PDEs. Ou…

2020-03-07math.OC

A Splitting Method For Overcoming the Curse of Dimensionality in Hamilton-Jacobi Equations Arising from Nonlinear Optimal Control and Differential Games with Applications to Trajectory Generation

Recent observations have been made that bridge splitting methods arising from optimization, to the Hopf and Lax formulas for Hamilton-Jacobi Equations with Hamiltonians $H(p)$. This has produced extremely fast algorithms in computing solutions of these PDEs. More recent observations were made in generalizing the Hopf and Lax formulas to state-and-time-dependent cases $H(x,p,t)$. In this article, we apply a new splitting method based on the Primal Dual Hybrid Gradient algorithm (a.k.a. Chambolle-Pock) to nonlinear optimal control and differential games problems, based on techniques from the der…

2018-03-03math.OC

Algorithm for Overcoming the Curse of Dimensionality for State-dependent Hamilton-Jacobi equations

In this paper, we develop algorithms to overcome the curse of dimensionality in possibly non-convex state-dependent Hamilton-Jacobi equations (HJ PDEs) arising from optimal control and differential game problems. The subproblems are independent and can be implemented in an embarrassingly parallel fashion. This is an ideal setup for perfect scaling in parallel computing. The algorithm is proposed to overcome the curse of dimensionality [1, 2] when solving HJ PDE. The major contribution of the paper is to change an optimization problem over a space of curves to an optimization problem of a singl…

2018-02-15math.APmath.OC

Algorithms for Overcoming the Curse of Dimensionality for Certain Hamilton-Jacobi Equations Arising in Control Theory and Elsewhere

It is well known that time dependent Hamilton-Jacobi-Isaacs partial differential equations (HJ PDE), play an important role in analyzing continuous dynamic games and control theory problems. An important tool for such problems when they involve geometric motion is the level set method. This was first used for reachability problems. The cost of these algorithms, and, in fact, all PDE numerical approximations is exponential in the space dimension and time. In this work we propose and test methods for solving a large class of the HJ PDE relevant to optimal control problems without the use of grid…

2016-05-06math.OC

Toward breaking the curse of dimensionality: an FPTAS for stochastic dynamic programs with multidimensional actions and scalar states

We propose a Fully Polynomial-Time Approximation Scheme (FPTAS) for stochastic dynamic programs with multidimensional action, scalar state, convex costs and linear state transition function. The action spaces are polyhedral and described by parametric linear programs. This type of problems finds applications in the area of optimal planning under uncertainty, and can be thought of as the problem of optimally managing a single non-discrete resource over a finite time horizon. We show that under a value oracle model for the cost functions this result for one-dimensional state space is "best possi…

2018-11-28cs.DMmath.OC

Perspectives on characteristics based curse-of-dimensionality-free numerical approaches for solving Hamilton-Jacobi equations

This paper extends the considerations of the works [1, 2] regarding curse-of-dimensionality-free numerical approaches to solve certain types of Hamilton-Jacobi equations arising in optimal control problems, differential games and elsewhere. A rigorous formulation and justification for the extended Hopf-Lax formula of [2] is provided together with novel theoretical and practical discussions including useful recommendations. By using the method of characteristics, the solutions of some problem classes under convexity/concavity conditions on Hamiltonians (in particular, the solutions of Hamilton-…

2017-11-09math.OC

更多相关论文收起更多论文

基于最大加法的近似方法中的维度灾难缩减：理论估计与改进的剪枝算法

Curse of dimensionality reduction in max-plus based approximation methods: theoretical estimates and improved pruning algorithms

INRIA（法国国家信息与自动化研究所）；CMAP École Polytechnique（巴黎综合理工学院数学与应用数学中心）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）；Fudan University（复旦大学）

针对最大加法近似方法中值函数逼近的维度灾难问题，提出理论误差估计并改进剪枝算法，以更少的基函数达到更高精度。

2011-09-24cs.SYeess.SYmath.OC

凸向量优化问题有效前沿的深度学习

Deep Learning the Efficient Frontier of Convex Vector Optimization Problems

本文设计了一种神经网络架构，用于近似满足 Slater 条件的凸向量优化问题的弱有效前沿，提供内外逼近及误差上界，并在大规模问题上克服了维度灾难。

2024-05-30math.OCq-fin.MFq-fin.RM

值函数的多面体逼近与测度最优量化之间的对偶性

Duality between polyhedral approximation of value functions and optimal quantization of measures

EDF Lab Paris-Saclay（法国电力巴黎萨克雷实验室）；INRIA（法国国家信息与自动化研究所）；CMAP, École polytechnique, Institut Polytechnique de Paris（巴黎综合理工学院数学与应用中心，巴黎理工学院）

该研究建立了凸函数多面体逼近与正测度最优量化的对偶关系，提出基于Newton多面体顶点聚类的贪心简约逼近方法，在量子门合成、电价双层优化中验证了有效性。

2025-09-04math.OC

On the convergence of gradient descent for two layer neural networks

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing works, we investigate the gradient descent method for training two-layer neural networks for approximating some target continuous functions. By making use the generic chaining technique from probability theory, we show that gradient descent can yield an exponential convergence rate, while the width of the neural networks needed is independent of the size of th…

2019-11-04cs.LGmath.OCstat.ML

部分信息下流行病随机最优控制

Stochastic Optimal Control of an Epidemic Under Partial Information

本文针对部分可观测随机流行病模型，提出将滤波与扩散近似相结合的最优控制框架，并用最优量化方法数值求解贝尔曼方程，验证了两种值函数近似方法的有效性。

2025-03-09math.OC