Search Results for author:
Found 5 papers, 0 papers with code
A Bandit Approach to Sequential Experimental Design with False Discovery Control
We propose a new adaptive sampling approach to multiple testing which aims to maximize statistical power while ensuring anytime false discovery control.
The Power of Adaptivity in Identifying Statistical Alternatives
This paper studies the trade-off between two different kinds of pure exploration: breadth versus depth.
NEXT: A System for Real-World Development, Evaluation, and Application of Active Learning
Active learning methods automatically adapt data collection by selecting the most informative samples in order to accelerate machine learning.
Query Complexity of Derivative-Free Optimization
Moreover, if the function evaluations are noisy, then approximating gradients by finite differences is difficult.
Active Ranking using Pairwise Comparisons
We show that under this assumption the number of possible rankings grows like $n^{2d}$ and demonstrate an algorithm that can identify a randomly selected ranking using just slightly more than $d log n$ adaptively selected pairwise comparisons, on average.
