Reproduce “Kernel Distributionally Robust Optimization” 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
Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf
Kernel DRO optimizes against the worst distribution in a set defined by kernel mean embeddings. Its dual uses an RKHS function that upper-bounds loss across the input domain, without requiring the loss to belong to a known RKHS or have a known Lipschitz constant. In uncertain least squares, it shows an intermediate robustness–optimality tradeoff, not a general shift guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.