Reproduce “Uncertainty Quantification of Next Generation Reservoir Computing with Applications to Memory-Driven Dynamical Systems” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Livia Popa, Sumanta Basu, Martin T. Wells
The paper compares Bayesian ridge and split conformal intervals for forecasts from next generation reservoir computing (NGRC). Both use the same ridge readout, but Bayesian width reflects prediction-error scale while conformal width reflects an absolute-error quantile. After a simulated noise shift, adaptive conformal reaches 0.938 coverage versus 0.595 for frozen split conformal, with wider intervals; results are not a general guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.