资源分类
》 资源 》论文》Near-Optimal Design of Experiments via Regret Minimization

Near-Optimal Design of Experiments via Regret Minimization

2020-03-09 | |  72 |   33 |   0

Abstract

We consider computationally tractable methods for the experimental design problem, where k out of n design points of dimension p are selected so that certain optimality criteria are approximately satisfied. Our algorithm finds a (1 + ε)approximate optimal design when k is a linear function of p; in contrast, existing results requir k to be super-linear in p. Our algorithm also handles all popular optimality criteria, while existin ones only handle one or two such criteria. Numerical results on synthetic and real-world design problems verify the practical effectiveness of the proposed algorithm.

上一篇：Robust Gaussian Graphical Model Estimation with Arbitrary Corruption

下一篇：Robust Submodular Maximization: A Non-Uniform Partitioning Approach

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...