arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.06277cs.LGcs.AImath.OC
收藏

利用深度网络与变分原理求解泛函优化问题

Solving Functional Optimization with Deep Networks and Variational Principles

Carnegie Mellon University(卡内基梅隆大学);CMKL University(CMKL大学)

Kawisorn Kamtue, Jose M. F. Moura, Orathai Sangpetch

AI总结:

本文提出 CalVNet,将变分法必要条件嵌入深度网络,在无真实数据条件下以无监督方式求解泛函优化问题,成功推导 Kalman 滤波、bang-bang 控制与流形测地线。

摘要:

神经网络能否仅凭第一性原理解决数学问题?本文展示了如何利用变分法的基本定理来设计深度神经网络,从而在无需训练数据(例如真实最优解)的情况下求解泛函优化问题。当解是定义在未知区间或支撑集上的函数时——例如在最小时间控制问题中——我们的方法尤为关键。通过将变分法推导出的最优函数解所需满足的必要条件融入深度架构的设计中,CalVNet 利用过参数化神经网络直接学习这些最优函数。我们验证了 CalVNet:在不依赖真实数据、仅融入第一性原理的情况下,它成功推导出线性滤波的 Kalman 滤波器、最小时间问题的 bang-bang 最优控制,并找到流形上的测地线。结果表明,CalVNet 能够以无监督方式进行训练,不依赖真实数据,从而为解决那些仍缺乏解析解的、可能尚未解决的一般性泛函优化问题建立了一个有前景的框架。

英文摘要:

Can neural networks solve math problems using first a principle alone? This paper shows how to leverage the fundamental theorem of the calculus of variations to design deep neural networks to solve functional optimization without requiring training data (e.g., ground-truth optimal solutions). Our approach is particularly crucial when the solution is a function defined over an unknown interval or support\textemdash such as in minimum-time control problems. By incorporating the necessary conditions satisfied by the optimal function solution, as derived from the calculus of variation, in the design of the deep architecture, CalVNet leverages overparameterized neural networks to learn these optimal functions directly. We validate CalVNet by showing that, without relying on ground-truth data and simply incorporating first principles, it successfully derives the Kalman filter for linear filtering, the bang-bang optimal control for minimum-time problems, and finds geodesics on manifolds. Our results demonstrate that CalVNet can be trained in an unsupervised manner, without relying on ground-truth data, establishing a promising framework for addressing general, potentially unsolved functional optimization problems that still lack analytical solutions.

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。

↑