A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions
Matteo Raviola, Benjamin Peherstorfer
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 0aa32fba-9f86-4288-8f13-88aab77fb5e9Builds on6
- Implicit Neural Spatial Representations for Time-dependent PDEsHonglin Chen, Rundi Wu, Eitan Grinspun, Changxi Zheng et al.ICML 2023 · 54 citations
- Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep NetworksJules Berman, Benjamin PeherstorferNeurIPS 2023 · 42 citations
- Improving Energy Natural Gradient Descent through Woodbury, Momentum, and RandomizationAndrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager, Marius ZeinhoferNeurIPS 2025 · 17 citations
- CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equationsJules Berman, Benjamin PeherstorferICML 2024 · 17 citations
- Achieving High Accuracy with PINNs via Energy Natural Gradient DescentJohannes Müller, Marius ZeinhoferICML 2023 · 13 citations
Related papers
- Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE ConstraintsHui Li, Huafeng Liu, Chenguang Li, Tianxiao Zhang et al.ICML 2026
- Self-Consistent Velocity Matching of Probability FlowsLingxiao Li, Samuel Hurault, Justin M. SolomonNeurIPS 2023 · 28 citations
- Differential Spectral Normalization (DSN) for PDE DiscoveryChi Chiu So, Tsz On Li, Chufang Wu, Siu Pang YungAAAI 2021 · 12 citations
- Machine learning structure preserving brackets for forecasting irreversible processesKookjin Lee, Nathaniel Trask, Panos StinisNeurIPS 2021 · 80 citations
- A Stable and Scalable Method for Solving Initial Value PDEs with Neural NetworksMarc Anton Finzi, Andres Potapczynski, Matthew Choptuik, Andrew Gordon WilsonICLR 2023 · 1 citation
