Show newer

Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees arxiv.org/abs/2410.18153

Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees

We propose the first learning scheme for functional differential equations (FDEs). FDEs play a fundamental role in physics, mathematics, and optimal control. However, the numerical analysis of FDEs has faced challenges due to its unrealistic computational costs and has been a long standing problem over decades. Thus, numerical approximations of FDEs have been developed, but they often oversimplify the solutions. To tackle these two issues, we propose a hybrid approach combining physics-informed neural networks (PINNs) with the \textit{cylindrical approximation}. The cylindrical approximation expands functions and functional derivatives with an orthonormal basis and transforms FDEs into high-dimensional PDEs. To validate the reliability of the cylindrical approximation for FDE applications, we prove the convergence theorems of approximated functional derivatives and solutions. Then, the derived high-dimensional PDEs are numerically solved with PINNs. Through the capabilities of PINNs, our approach can handle a broader class of functional derivatives more efficiently than conventional discretization-based methods, improving the scalability of the cylindrical approximation. As a proof of concept, we conduct experiments on two FDEs and demonstrate that our model can successfully achieve typical $L^1$ relative error orders of PINNs $\sim 10^{-3}$. Overall, our work provides a strong backbone for physicists, mathematicians, and machine learning experts to analyze previously challenging FDEs, thereby democratizing their numerical analysis, which has received limited attention. Code is available at \url{https://github.com/TaikiMiyagawa/FunctionalPINN}.

arXiv.org

Two-stage heuristic algorithm for a new variant of the multi-compartment vehicle routing problem with stochastic demands arxiv.org/abs/2410.17302

Two-stage heuristic algorithm for a new variant of the multi-compartment vehicle routing problem with stochastic demands

This paper presents a model for a vehicle routing problem in which customer demands are stochastic and vehicles are divided into compartments. The problem is motivated by the needs of certain agricultural cooperatives that produce various types of livestock food. The vehicles and their compartments have different capacities, and each compartment can only contain one type of feed. Additionally, certain farms can only be accessed by specific vehicles, and there may be urgency constraints. To solve the problem, a two-step heuristic algorithm is proposed. First, a constructive heuristic is applied, followed by an improvement phase based on iterated tabu search. The designed algorithm is tested on several instances, including an analysis of real-world datasets where the results are compared with those provided by the model. Furthermore, multiple benchmark instances are created for this problem and an extensive simulation study is conducted. Results are presented for different model parameters, and it is shown that, despite the problems' complexity, the algorithm performs efficiently. Finally, the proposed heuristic is compared to existing solution algorithms for similar problems using benchmark instances from the literature, achieving competitive results.

arXiv.org
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.