Leveraging Hamilton-Jacobi PDEs with time-dependent Hamiltonians for continual scientific machine learning

• URL: http://arxiv.org/abs/2311.07790v2
• Date: Mon, 6 May 2024 19:10:34 GMT
• Title: Leveraging Hamilton-Jacobi PDEs with time-dependent Hamiltonians for continual scientific machine learning
• Authors: Paula Chen, Tingwei Meng, Zongren Zou, Jérôme Darbon, George Em Karniadakis,
• Abstract summary: We address two major challenges in scientific machine learning (SciML) We establish a new theoretical connection between optimization problems arising from SciML and a generalized Hopf formula. Existing HJ PDE solvers and optimal control algorithms can be reused to design new efficient training approaches.
• Score: 1.8175282137722093
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We address two major challenges in scientific machine learning (SciML): interpretability and computational efficiency. We increase the interpretability of certain learning processes by establishing a new theoretical connection between optimization problems arising from SciML and a generalized Hopf formula, which represents the viscosity solution to a Hamilton-Jacobi partial differential equation (HJ PDE) with time-dependent Hamiltonian. Namely, we show that when we solve certain regularized learning problems with integral-type losses, we actually solve an optimal control problem and its associated HJ PDE with time-dependent Hamiltonian. 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. As a result, existing HJ PDE solvers and optimal control algorithms can be reused to design new efficient training approaches for SciML that naturally coincide with the continual learning framework, while avoiding catastrophic forgetting. As a first exploration of this connection, we consider the special case of linear regression and leverage our connection to develop a new Riccati-based methodology for solving these learning problems that is amenable to continual learning applications. We also provide some corresponding numerical examples that demonstrate the potential computational and memory advantages our Riccati-based approach can provide.

Related papers

• A Deep Learning approach for parametrized and time dependent Partial Differential Equations using Dimensionality Reduction and Neural ODEs [46.685771141109306]
  We propose an autoregressive and data-driven method using the analogy with classical numerical solvers for time-dependent, parametric and (typically) nonlinear PDEs. We show that by leveraging DR we can deliver not only more accurate predictions, but also a considerably lighter and faster Deep Learning model.
  arXiv  Detail & Related papers  (2025-02-12T11:16:15Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs) We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations. We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• Leveraging viscous Hamilton-Jacobi PDEs for uncertainty quantification in scientific machine learning [1.8175282137722093]
  Uncertainty (UQ) in scientific machine learning (SciML) combines the powerful predictive power of SciML with methods for quantifying the reliability of the learned models. We provide a new interpretation for UQ problems by establishing a new theoretical connection between some Bayesian inference problems arising in SciML and viscous Hamilton-Jacobi partial differential equations (HJ PDEs) We develop a new Riccati-based methodology that provides computational advantages when continuously updating the model predictions.
  arXiv  Detail & Related papers  (2024-04-12T20:54:01Z)
• Self-Supervised Learning with Lie Symmetries for Partial Differential Equations [25.584036829191902]
  We learn general-purpose representations of PDEs by implementing joint embedding methods for self-supervised learning (SSL) Our representation outperforms baseline approaches to invariant tasks, such as regressing the coefficients of a PDE, while also improving the time-stepping performance of neural solvers. We hope that our proposed methodology will prove useful in the eventual development of general-purpose foundation models for PDEs.
  arXiv  Detail & Related papers  (2023-07-11T16:52:22Z)
• An Optimization-based Deep Equilibrium Model for Hyperspectral Image Deconvolution with Convergence Guarantees [71.57324258813675]
  We propose a novel methodology for addressing the hyperspectral image deconvolution problem. A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Leveraging Multi-time Hamilton-Jacobi PDEs for Certain Scientific Machine Learning Problems [1.6874375111244329]
  Hamilton-Jacobi partial differential equations (HJ PDEs) have deep connections with a wide range of fields. We establish a novel theoretical connection between specific optimization problems arising in machine learning and the multi-time Hopf formula. We show that when we solve these learning problems, we also solve a multi-time HJ PDE and, by extension, its corresponding optimal control problem.
  arXiv  Detail & Related papers  (2023-03-22T21:55:30Z)
• Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs [3.249853429482705]
  A state-dependent Riccati equation control law is first used to generate a gradient-augmented synthetic dataset for supervised learning. The resulting model becomes a warm start for the minimization of a loss function based on the residual of the HJB PDE.
  arXiv  Detail & Related papers  (2022-07-19T14:34:07Z)
• Learning differentiable solvers for systems with hard constraints [48.54197776363251]
  We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs) We develop a differentiable PDE-constrained layer that can be incorporated into any NN architecture. Our results show that incorporating hard constraints directly into the NN architecture achieves much lower test error when compared to training on an unconstrained objective.
  arXiv  Detail & Related papers  (2022-07-18T15:11:43Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.