Adversarial Smoothed Analysis
arXiv:0903.34997 citations
Originality Synthesis-oriented
AI Analysis
Provides a theoretical robustness result for smoothed analysis under adversarial perturbation distributions.
This work extends uniform smoothed analysis of condition numbers to radially symmetric perturbations with a singularity at the center, showing that previous bounds still hold.
The purpose of this note is to extend the results on uniform smoothed analysis of condition numbers from \cite{BuCuLo:07} to the case where the perturbation follows a radially symmetric probability distribution. In particular, we will show that the bounds derived in \cite{BuCuLo:07} still hold in the case of distributions whose density has a singularity at the center of the perturbation, which we call {\em adversarial}.