AI RESEARCH
Learning Confidence Ellipsoids and Applications to Robust Subspace Recovery
arXiv CS.LG
•
ArXi:2512.16875v4 Announce Type: replace-cross We study the problem of finding confidence ellipsoids for an arbitrary distribution in high dimensions. Given samples from a distribution $D$ and a confidence parameter $\alpha$, the goal is to find the smallest volume ellipsoid $E$ which has probability mass $\mathbb{P}_{D}[E] \ge 1-\alpha$. Ellipsoids are a highly expressive class of confidence sets as they can capture correlations in the distribution, and can approximate any convex set.