Timezone: »

Near-Optimal Design of Experiments via Regret Minimization
Zeyuan Allen-Zhu · Yuanzhi Li · Aarti Singh · Yining Wang

Wed Aug 09 01:30 AM -- 05:00 AM (PDT) @ Gallery #124

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+eps)-approximate optimal design when k is a linear function of p; in contrast, existing results require k to be super-linear in p. Our algorithm also handles all popular optimality criteria, while existing 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.

Author Information

Zeyuan Allen-Zhu (Microsoft Research / Princeton / IAS)
Yuanzhi Li (Princeton University)
Aarti Singh (Carnegie Mellon University)
Yining Wang (CMU)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors