no code implementations • 12 Apr 2024 • Zongren Zou, Tingwei Meng, Paula Chen, Jérôme Darbon, George Em Karniadakis
We provide several examples from SciML involving noisy data and \textit{epistemic uncertainty} to illustrate the potential advantages of our approach.
no code implementations • 11 Mar 2024 • Gabriel P. Langlois, Jatan Buch, Jérôme Darbon
State-of-the-art algorithms for Maxent models, however, were not originally designed to handle big data sets; these algorithms either rely on technical devices that may yield unreliable numerical results, scale poorly, or require smoothness assumptions that many practical Maxent models lack.
no code implementations • 13 Nov 2023 • Paula Chen, Tingwei Meng, Zongren Zou, Jérôme Darbon, George Em Karniadakis
This connection allows us to reinterpret incremental updates to learned models as the evolution of an associated HJ PDE and optimal control problem in time, where all of the previous information is intrinsically encoded in the solution to the HJ PDE.
1 code implementation • 22 Mar 2023 • Paula Chen, Tingwei Meng, Zongren Zou, Jérôme Darbon, George Em Karniadakis
Hamilton-Jacobi partial differential equations (HJ PDEs) have deep connections with a wide range of fields, including optimal control, differential games, and imaging sciences.
1 code implementation • 14 Jan 2022 • Tingwei Meng, Zhen Zhang, Jérôme Darbon, George Em Karniadakis
Solving high-dimensional optimal control problems in real-time is an important but challenging problem, with applications to multi-agent path planning problems, which have drawn increased attention given the growing popularity of drones in recent years.
no code implementations • 30 Nov 2021 • Jérôme Darbon, Gabriel P. Langlois
Since modern big data sets can contain hundreds of thousands to billions of predictor variables, variable selection methods depend on efficient and robust optimization algorithms to perform well.
no code implementations • 24 Sep 2021 • Jérôme Darbon, Gabriel P. Langlois
To address this issue, we introduce accelerated nonlinear PDHG methods that achieve an optimal convergence rate with stepsize parameters that are simple and efficient to compute.
1 code implementation • 28 May 2021 • Jérôme Darbon, Tingwei Meng, Elena Resmerita
We show that the optimal values are ruled by some Hamilton-Jacobi PDEs, while the optimizers are characterized by the spatial gradient of the solution to the Hamilton-Jacobi PDEs.
1 code implementation • 7 May 2021 • Jérôme Darbon, Peter M. Dower, Tingwei Meng
In this paper, we propose two abstract neural network architectures which are respectively used to compute the value function and the optimal control for certain class of high dimensional optimal control problems.
no code implementations • 22 Apr 2021 • Jérôme Darbon, Gabriel P. Langlois, Tingwei Meng
In [23, 26], connections between these optimization problems and (multi-time) Hamilton--Jacobi partial differential equations have been proposed under the convexity assumptions of both the data fidelity and regularization terms.
no code implementations • 6 Apr 2021 • Yeonjong Shin, Jérôme Darbon, George Em Karniadakis
We propose three versions -- non-adaptive, adaptive terminal and adaptive order.
no code implementations • 4 Feb 2021 • Marceau Coupechoux, Jérôme Darbon, Jean-Marc Kélif, Marc Sigelle
We derive closed-form formulas for the optimal trajectory when the traffic intensity is quadratic (single-phase) using Hamilton-Jacobi equations.
Optimization and Control Networking and Internet Architecture
1 code implementation • 22 Feb 2020 • Jérôme Darbon, Tingwei Meng
We propose novel connections between several neural network architectures and viscosity solutions of some Hamilton--Jacobi (HJ) partial differential equations (PDEs) whose Hamiltonian is convex and only depends on the spatial gradient of the solution.
Numerical Analysis Numerical Analysis