CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations

• URL: http://arxiv.org/abs/2402.14646v2
• Date: Sun, 21 Jul 2024 15:11:04 GMT
• Title: CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
• Authors: Jules Berman, Benjamin Peherstorfer,
• Abstract summary: Continuous Low Rank Adaptation (CoLoRA) Adaptation can be either purely data-driven or via an equation-driven variational approach. Because CoLoRA approximates solution fields locally in time, the rank of the weights can be kept small.
• Score: 1.2935057904849894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work introduces reduced models based on Continuous Low Rank Adaptation (CoLoRA) that pre-train neural networks for a given partial differential equation and then continuously adapt low-rank weights in time to rapidly predict the evolution of solution fields at new physics parameters and new initial conditions. The adaptation can be either purely data-driven or via an equation-driven variational approach that provides Galerkin-optimal approximations. Because CoLoRA approximates solution fields locally in time, the rank of the weights can be kept small, which means that only few training trajectories are required offline so that CoLoRA is well suited for data-scarce regimes. Predictions with CoLoRA are orders of magnitude faster than with classical methods and their accuracy and parameter efficiency is higher compared to other neural network approaches.

Related papers

• ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations [54.886931928255564]
  Low-rank adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning method in deep transfer learning.<n>We propose a novel continuous-time optimization dynamic for LoRA factor matrices in the form of an ordinary differential equation (ODE)<n>We show that ODELoRA achieves stable feature learning, a property that is crucial for training deep neural networks at different scales of problem dimensionality.
  arXiv  Detail & Related papers  (2026-02-07T10:19:36Z)
• MAD-NG: Meta-Auto-Decoder Neural Galerkin Method for Solving Parametric Partial Differential Equations [5.767740428776141]
  Parametric partial differential equations (PDEs) are fundamental for modeling a wide range of physical and engineering systems.<n>Traditional neural network-based solvers, such as Physics-Informed Neural Networks (PINNs) and Deep Galerkin Methods, often face challenges in generalization and long-time prediction efficiency.<n>We propose a novel and scalable framework that significantly enhances the Neural Galerkin Method (NGM) by incorporating the Meta-Auto-Decoder (MAD) paradigm.
  arXiv  Detail & Related papers  (2025-12-25T11:27:40Z)
• Mitigating Forgetting in Low Rank Adaptation [17.859306837144732]
  We present LaLoRA, a weight-space regularization technique that applies a Laplace approximation to Low-Rank Adaptation.<n>Our approach estimates the model's confidence in each parameter and constrains updates in high-curvature directions.<n>We evaluate LaLoRA by fine-tuning a Llama model for mathematical reasoning and demonstrate an improved learning-forgetting trade-off.
  arXiv  Detail & Related papers  (2025-12-19T15:54:36Z)
• Convolution-weighting method for the physics-informed neural network: A Primal-Dual Optimization Perspective [14.65008276932511]
  Physics-informed neural networks (PINNs) are extensively employed to solve partial differential equations (PDEs)<n>PINNs are typically optimized using a finite set of points, which poses significant challenges in guaranteeing their convergence and accuracy.<n>We propose a new weighting scheme that will adaptively change the weights to the loss functions from isolated points to their continuous neighborhood regions.
  arXiv  Detail & Related papers  (2025-06-24T17:13:51Z)
• LaPON: A Lagrange's-mean-value-theorem-inspired operator network for solving PDEs and its application on NSE [8.014720523981385]
  We propose LaPON, an operator network inspired by the Lagrange's mean value theorem.<n>It embeds prior knowledge directly into the neural network architecture instead of the loss function.<n>LaPON provides a scalable and reliable solution for high-fidelity fluid dynamics simulation.
  arXiv  Detail & Related papers  (2025-05-18T10:45:17Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models [26.808251361020066]
  Fine-tuning pre-trained models often yields state-of-the-art performance but is computationally expensive when updating all parameters. We propose NEAT, a nonlinear PEFT approach that employs a lightweight neural network to learn a nonlinear transformation of the pre-trained weights. Our theoretical analysis shows that NEAT achieves greater efficiency than LoRA while maintaining equivalent expressivity.
  arXiv  Detail & Related papers  (2024-10-02T17:29:23Z)
• FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems [41.94295877935867]
  numerical simulation and optimization of technical systems described by partial differential equations is expensive. A comparatively new approach in this context is to combine the good approximation properties of neural networks with the classical finite element method. In this paper, we extend this approach to saddle-point and non-linear fluid dynamics problems, respectively.
  arXiv  Detail & Related papers  (2024-09-06T07:17:01Z)
• Neural Parameter Regression for Explicit Representations of PDE Solution Operators [22.355460388065964]
  We introduce Neural Regression (NPR), a novel framework specifically developed for learning solution operators in Partial Differential Equations (PDEs) NPR employs Physics-Informed Neural Network (PINN, Raissi et al., 2021) techniques to regress Neural Network (NN) parameters. The framework shows remarkable adaptability to new initial and boundary conditions, allowing for rapid fine-tuning and inference.
  arXiv  Detail & Related papers  (2024-03-19T14:30:56Z)
• Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models [45.72323731094864]
  Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method. In this work, we study the enhancement of LoRA training by introducing an $r times r$ preconditioner in each gradient step.
  arXiv  Detail & Related papers  (2024-02-04T05:05:43Z)
• SPDE priors for uncertainty quantification of end-to-end neural data assimilation schemes [4.213142548113385]
  Recent advances in the deep learning community enables to adress this problem as neural architecture embedding data assimilation variational framework. In this work, we draw from SPDE-based Processes to estimate prior models able to handle non-stationary covariances in both space and time. Our neural variational scheme is modified to embed an augmented state formulation with both state SPDE parametrization to estimate.
  arXiv  Detail & Related papers  (2024-02-02T19:18:12Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• A Neural Network-Based Enrichment of Reproducing Kernel Approximation for Modeling Brittle Fracture [0.0]
  An improved version of the neural network-enhanced Reproducing Kernel Particle Method (NN-RKPM) is proposed for modeling brittle fracture. The effectiveness of the proposed method is demonstrated by a series of numerical examples involving damage propagation and branching.
  arXiv  Detail & Related papers  (2023-07-04T21:52:09Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations [63.8376359764052]
  We propose an approach to solving partial differential equations (PDEs) using a set of neural networks. We regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE.
  arXiv  Detail & Related papers  (2022-08-02T18:27:13Z)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions [47.276004075767176]
  We develop software for convex optimization of two-layer neural networks with ReLU activation functions.<n>We show that convex gated ReLU models obtain data-dependent algorithms for the ReLU training problem.
  arXiv  Detail & Related papers  (2022-02-02T23:50:53Z)
• On feedforward control using physics-guided neural networks: Training cost regularization and optimized initialization [0.0]
  Performance of model-based feedforward controllers is typically limited by the accuracy of the inverse system dynamics model. This paper proposes a regularization method via identified physical parameters. It is validated on a real-life industrial linear motor, where it delivers better tracking accuracy and extrapolation.
  arXiv  Detail & Related papers  (2022-01-28T12:51:25Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.