How many continuous measurements are needed to learn a vector?
Abstract
One can recover vectors from R m \mathbb {R}^m with arbitrary precision, using only ⌈ log 2 ( m ) ⌉ + 1 \lceil \log _2(m)\rceil +1 continuous measurements that are chosen adaptively. This surprising result is explained and discussed, and we present applications to infinite-dimensional approximation problems.
Fields of Study & Subjects
Fault Detection and Control Systems
Neural Networks and Applications
Publication details
- Journal / source
- Proceedings of the American Mathematical Society
- Publication date
- 2 September 2026
- Language
- EN