Affiliation:
1. School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332;
2. Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, Virginia 24061
Abstract
Experimental design is a classical statistics problem, and its aim is to estimate an unknown vector from linear measurements where a Gaussian noise is introduced in each measurement. For the combinatorial experimental design problem, the goal is to pick a subset of experiments so as to make the most accurate estimate of the unknown parameters. In this paper, we will study one of the most robust measures of error estimation—the D-optimality criterion, which corresponds to minimizing the volume of the confidence ellipsoid for the estimation error. The problem gives rise to two natural variants depending on whether repetitions of experiments are allowed or not. We first propose an approximation algorithm with a 1/e-approximation for the D-optimal design problem with and without repetitions, giving the first constant-factor approximation for the problem. We then analyze another sampling approximation algorithm and prove that it is asymptotically optimal. Finally, for D-optimal design with repetitions, we study a different algorithm proposed by the literature and show that it can improve this asymptotic approximation ratio. All the sampling algorithms studied in this paper are shown to admit polynomial-time deterministic implementations.
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Subject
Management Science and Operations Research,Computer Science Applications,General Mathematics
Reference35 articles.
1. Allen-Zhu Z, Liao Z, Orecchia L (2015) Spectral sparsification and regret minimization beyond matrix multiplicative updates. Proc. 47th Annual ACM Sympos. Theory Comput. (ACM, New York), 237–245.
2. Allen-Zhu Z, Li Y, Singh A, Wang Y (2017) Near-optimal design of experiments via regret minimization. Proc. 34th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 70 (PMLR), 126–135.
3. Avron H, Boutsidis C, Toledo S, Zouzias A (2013) Efficient dimensionality reduction for canonical correlation analysis. Proc. 30th Internat. Conf. Machine Learn. (ICML-13), Proceedings Machine Learning Research, vol. 28(PMLR), 347–355.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献