Radon's theorem is a result in convex geometry that deals with the intersection of convex sets. Specifically, it states that: **Radon's Theorem:** If a set of \( d + 2 \) points in \( \mathbb{R}^d \) is given, then it is possible to partition these points into two non-empty subsets such that the convex hulls (the smallest convex sets containing the points) of these two subsets intersect.
Articles by others on the same topic
Every set of at least points in can be partitioned into two nonempty parts with intersecting convex hulls. To see this, take a nonzero affine dependence on of its points. Its positive and negative coefficient sums have the same magnitude . Dividing by expresses one point as a convex combination of the positive-coefficient points and also as a convex combination of the negative-coefficient points. Distribute zero-coefficient and remaining points arbitrarily between the parts. This theorem obstructs arbitrary labels for affine linear classifiers.