Reproduce “Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions” 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
Heiner Kremer, Jia-Jie Zhu, Krikamol Muandet, Bernhard Schölkopf
Functional GEL (FGEL) extends generalized empirical likelihood to conditional moment restrictions by using flexible instrument functions to test moments and regularization to manage the resulting continuum of checks. Its kernel implementation has conditional-moment guarantees under stated assumptions, while neural theory remains open. In experiments, FGEL performs well against VMM, but results are task-specific and do not establish general superiority.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.