Random features approximate Koopman generators of continuous-time systems
A data-informed dictionary for gEDMD is reported faster than iterative optimization, with convergence proofs and a boundedness counterexample.
Stories per day · 30 days
Relatedapproximation-theory1dynamical-systems1forecasting1gedmd1koopman1neural-networks1rkhs1training1
2 stories, newest first · one card per story
Stories tagged #random-features
Partially trainable networks show a sharp approximation phase transition
For spherical biased-ReLU features at d=5 and τ=10, about 4.1% trainable width captures 90% of the bound reduction.