A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions
Matteo Raviola, Benjamin Peherstorfer
摘要
Dirac-Frenkel instantaneous residual minimization evolves nonlinear parametrizations of PDE solutions in time, but ill-conditioning can render the parameter dynamics non-unique. We interpret this non-uniqueness as a gauge freedom: nullspace directions that leave the time derivative unchanged can be used to select better-conditioned parameter velocities. Building on Onsager's minimum-dissipation principle, we introduce a history variable---interpretable as momentum---and inject it only along the nullspace directions. The resulting Dirac-Frenkel-Onsager dynamics preserve instantaneous residual minimization, in contrast to standard regularization that can introduce bias, while promoting temporally smooth parameter evolution. Examples demonstrate that the approach leads to increased robustness in singular and near-singular regimes.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper6
- Implicit Neural Spatial Representations for Time-dependent PDEsHonglin Chen, Rundi Wu, Eitan Grinspun, Changxi Zheng 等ICML 2023 · 被引用 54 次
- Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep NetworksJules Berman, Benjamin PeherstorferNeurIPS 2023 · 被引用 42 次
- Improving Energy Natural Gradient Descent through Woodbury, Momentum, and RandomizationAndrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager, Marius ZeinhoferNeurIPS 2025 · 被引用 17 次
- CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equationsJules Berman, Benjamin PeherstorferICML 2024 · 被引用 17 次
- Achieving High Accuracy with PINNs via Energy Natural Gradient DescentJohannes Müller, Marius ZeinhoferICML 2023 · 被引用 13 次
相关 Paper
- Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE ConstraintsHui Li, Huafeng Liu, Chenguang Li, Tianxiao Zhang 等ICML 2026
- Self-Consistent Velocity Matching of Probability FlowsLingxiao Li, Samuel Hurault, Justin M. SolomonNeurIPS 2023 · 被引用 28 次
- Differential Spectral Normalization (DSN) for PDE DiscoveryChi Chiu So, Tsz On Li, Chufang Wu, Siu Pang YungAAAI 2021 · 被引用 12 次
- Machine learning structure preserving brackets for forecasting irreversible processesKookjin Lee, Nathaniel Trask, Panos StinisNeurIPS 2021 · 被引用 80 次
- A Stable and Scalable Method for Solving Initial Value PDEs with Neural NetworksMarc Anton Finzi, Andres Potapczynski, Matthew Choptuik, Andrew Gordon WilsonICLR 2023 · 被引用 1 次
