Personalized PageRank on row-normalized EDMD matrices detects Koopman-invariant sub-dictionaries with O(1/sqrt(M)) finite-sample guarantees and is tested on standard chaotic systems.
Brunton, Joshua L
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
CTF4Nuclear proposes a common task framework for benchmarking ML methods on nuclear engineering datasets using 12 metrics and a new sparse-measurement system monitoring paradigm.
FePySR uses a neural network to pre-extract valid features before PySR search, recovering more equations than baselines on benchmarks and identifying governing ODEs in 24 of 100 biological cases where PySR finds none.
The paper introduces a Common Task Framework for scientific ML, benchmarks it on Kuramoto-Sivashinsky and Lorenz systems, and launches a competition on a global sea surface temperature dataset with holdout data.
A constrained least-squares (ADMM) learns a skew-symmetric derivative stencil for 1D Maxwell equations that conserves discrete energy exactly while matching centered-difference accuracy.
citing papers explorer
-
Finding Koopman Invariant Subspaces via Personalized PageRank
Personalized PageRank on row-normalized EDMD matrices detects Koopman-invariant sub-dictionaries with O(1/sqrt(M)) finite-sample guarantees and is tested on standard chaotic systems.
-
CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models
CTF4Nuclear proposes a common task framework for benchmarking ML methods on nuclear engineering datasets using 12 metrics and a new sparse-measurement system monitoring paradigm.
-
FePySR: A Neural Feature Extraction Framework for Efficient and Scalable Symbolic Regression
FePySR uses a neural network to pre-extract valid features before PySR search, recovering more equations than baselines on benchmarks and identifying governing ODEs in 24 of 100 biological cases where PySR finds none.
-
Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
The paper introduces a Common Task Framework for scientific ML, benchmarks it on Kuramoto-Sivashinsky and Lorenz systems, and launches a competition on a global sea surface temperature dataset with holdout data.
-
An Energy Stable Approach for Learning Derivative Operators from Noisy Data for Maxwells Equations
A constrained least-squares (ADMM) learns a skew-symmetric derivative stencil for 1D Maxwell equations that conserves discrete energy exactly while matching centered-difference accuracy.