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.
Learning deep neural network representations for Koopman operators of nonlinear dynamical systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Residual-guided neural dictionary learning reduces spectral pollution and improves forecast accuracy in Koopman approximations on benchmarks and sea-surface temperature data.
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.
-
Residual-Guided Dictionary Learning for Spectrally Accurate Koopman Approximation
Residual-guided neural dictionary learning reduces spectral pollution and improves forecast accuracy in Koopman approximations on benchmarks and sea-surface temperature data.