Experimental Design Using Interlacing Polynomials
Data Structures and Algorithms
2024-10-16 v1 Machine Learning
Computation
Machine Learning
Abstract
We present a unified deterministic approach for experimental design problems using the method of interlacing polynomials. Our framework recovers the best-known approximation guarantees for the well-studied D/A/E-design problems with simple analysis. Furthermore, we obtain improved non-trivial approximation guarantee for E-design in the challenging small budget regime. Additionally, our approach provides an optimal approximation guarantee for a generalized ratio objective that generalizes both D-design and A-design.
Cite
@article{arxiv.2410.11390,
title = {Experimental Design Using Interlacing Polynomials},
author = {Lap Chi Lau and Robert Wang and Hong Zhou},
journal= {arXiv preprint arXiv:2410.11390},
year = {2024}
}
Comments
16 pages