Reproduce “Gaussian Processes for Nonlinear Signal Processing” 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
Fernando Pérez-Cruz, Steven Van Vaerenbergh, Juan José Murillo-Fuentes, Miguel Lázaro-Gredilla, Ignacio Santamaria
The paper presents GPR as a nonlinear Bayesian extension of Wiener filtering; its mean matches kernel ridge regression, and its variance represents input-dependent uncertainty. It describes recursive forgetting for adaptation and evaluates KRLS-T on changing communication channels. On measured fast-fading data, KRLS-T reaches −21.3 dB steady-state NMSE versus −15.8 dB for QKLMS, in the specified setup, not universally.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.